Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 271. Отображено 100.
05-01-2017 дата публикации

HANDWRITTEN CHARACTER CORRECTION APPARATUS, HANDWRITTEN CHARACTER CORRECTION METHOD, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM

Номер: US20170004122A1
Автор: Higashi Hideto, Kataoka Masahiro, Taniguchi Yuji, TSUYUKI Yasuhiro
Принадлежит: FUJITSU LIMITED

A method that includes correcting at least one of a character image of a target replacement character or stroke information of the target replacement character, in response to a designation of a specific character among recognized characters from handwriting input and an input of the target replacement character that is to replace the specific character, and updating at least one of a character image of the recognized characters or a stroke image of the recognized characters by utilizing at least a corrected one of the character image or the stroke information. The at least one of the character image or the stroke information is corrected based on coordinate information corresponding to the specific character. The coordinate information is generated from at least one of the character image of the recognized characters or the stroke image of the recognized characters that are stored in a memory. 1. A non-transitory computer-readable recording medium storing therein a handwriting input recognition program that causes a computer to execute a process comprising:correcting at least one of a character image of a target replacement character or stroke information of the target replacement character, in response to a designation of a specific character among a plurality of recognized characters from handwriting input and an input of the target replacement character that is to replace the specific character; andupdating at least one of a character image of the plurality of recognized characters or a stroke image of the plurality of recognized characters by utilizing at least a corrected one of the character image of the target replacement character or the stroke information of the target replacement character;wherein the at least one of the character image of the target replacement character or the stroke information of the target replacement character is corrected based on coordinate information corresponding to the specific character; andwherein the coordinate information ...

Подробнее
Номер записи: 1
05-01-2017 дата публикации

System and Method for Efficient Recognition of Handwritten Characters in Documents

Номер: US20170004359A1
Автор: Baala Mithra Swaminathan Mithra, Radha Krishna Rao Geelapaturu Subrahmanya Venkata, Santosh Gauriar Anshuman, VENKATACHALAM Natarajan
Принадлежит:

A system and computer-implemented method for efficient recognition of one or more handwritten characters in one or more documents is provided. The system comprises an image input module configured to receive the one or more documents as one or more images. The system further comprises a snippet extraction module to extract one or more fields of information from the one or more received images. Furthermore, the system comprises a segmentation module to segment the one or more extracted fields of information into one or more segments. Also, the system comprises a feature extraction module configured to extract one or more handwritten characters from each of the one or more segments. In addition, the system comprises a character recognition module configured to recognize the one or more extracted handwritten characters. The system further comprises a language processing module configured to detect and correct errors in the one or more recognized characters. 1. A system for efficient recognition of one or more handwritten characters in one or more documents , the system comprising:an image input module configured to receive the one or more documents as one or more images;a snippet extraction module configured to extract one or more fields of information from the one or more received images;a segmentation module configured to segment the one or more extracted fields of information into one or more segments;a feature extraction module configured to extract one or more handwritten characters from each of the one or more segments;a character recognition module configured to recognize the one or more extracted handwritten characters; and analyzing content in the vicinity of each of the one or more recognized characters;', 'predicting one or more characters for each of the one or more recognized characters in the extracted fields of information based on the analyzed content;', 'comparing each of the one or more recognized characters with the one or more predicted characters ...

Подробнее
Номер записи: 2
04-01-2018 дата публикации

PATH SCORE CALCULATING METHOD FOR INTELLIGENT CHARACTER RECOGNITION

Номер: US20180005058A1
Автор: Yang Duanduan
Принадлежит: KONICA MINOLTA LABORATORY U.S.A., INC.

Disclosed herein is a method that improves the performance of handwriting recognition by calculating path scores so as to identify the path with the highest score as the basis for interpreting handwritten characters. Specifically, the method comprises the following steps: detecting connected regions in an input image comprising handwritten characters; determining a plurality of segmentation positions of the input image; obtaining a plurality of recognition results for each segment of each path in the input image, wherein each recognition result represents a character candidate for the segment and each path comprises one or more segments; obtaining a plurality of scores corresponding to the recognition results; calculating scores for each path in the input image based on segment lengths and the scores corresponding to the recognition results; and using the path with the highest score to interpret the handwritten characters in the input image. 1. A method for handwriting recognition , comprising:detecting connected regions in an input image comprising handwritten characters;determining a plurality of segmentation positions of the input image;obtaining a plurality of recognition results for each segment of each path in the input image, wherein each recognition result represents a character candidate for the segment and each path comprises one or more segments;obtaining a plurality of scores corresponding to the recognition results;calculating scores for each path in the input image based on segment lengths and the scores corresponding to the recognition results; andusing the path with the highest score to interpret the handwritten characters in the input image.2. The method of claim 1 , wherein the path score is calculated using the following equation: S=a*(S*Len+S*Len+ . . . +S*Len)+b*min (S claim 1 , S claim 1 , . . . claim 1 , S) claim 1 , wherein Len claim 1 , Len. . . Lenrepresent respective segment lengths for Seg claim 1 , Seg claim 1 , . . . Segof the path ...

Подробнее
Номер записи: 3
04-01-2018 дата публикации

SYSTEMS AND METHODS FOR RECOGNIZING CHARACTERS IN DIGITIZED DOCUMENTS

Номер: US20180005082A1
Автор: Bluche Theodore Damien Christian
Принадлежит:

Methods and systems are provided for end-to-end text recognition in digitized documents of handwritten characters over multiple lines without explicit line segmentation. An image is received. Based on the image, one or more feature maps are determined. Each of the one or more feature maps include one or more feature vectors. Based at least in part on the one or more feature maps, one or more scalar scores are determined. Based on the one or more scalar scores, one or more attention weights are determined. By applying the one or more attention weights to each of the one or more feature vectors, one or more image summary vectors are determined. Based at least in part on the one or more image summary vectors, one or more handwritten characters are determined. 1. A method of recognizing a plurality of handwritten characters over multiple lines , the method comprising:receiving an image of a document including a plurality of handwritten characters;determining, based at least in part on the image, a plurality of feature maps, each of which includes a plurality of feature vectors corresponding to the respective plurality of handwritten characters;determining, based at least in part on the plurality of feature maps, a plurality of scalar scores;determining, based on the plurality of scalar scores, a plurality of attention weights;determining, by applying the plurality of attention weights to each of the plurality of feature vectors, a plurality of image summary vectors; andrecognizing, based at least in part on the plurality of image summary vectors, the plurality of handwritten characters.2. The method of claim 1 , further comprising:determining the size of the image; andwherein the number of the plurality of feature maps is based at least in part on the size of the image.3. The method of claim 1 , further comprising:displaying the recognized plurality of handwritten characters on a display device.4. The method of claim 1 , wherein the recognized plurality of handwritten ...

Подробнее
Номер записи: 4
02-01-2020 дата публикации

AUTOMATIC GENERATION AND POPULATION OF DIGITAL INTERFACES BASED ON ADAPTIVELY PROCESSED IMAGE DATA

Номер: US20200005258A1
Автор: ABDULLAH OMAS, ESPOSITO HELENE NICOLE, FICHUK DEXTER LAMONT, Hum Patrick Jian Hong, MCPHEE Adam Douglas, MILLER ROBERT KYLE, ODOBETSKIY KYRYLL, REILLY HARRISON MICHAEL JAMES, TORBICA SONJA, WAKIM MATTA
Принадлежит:

The disclosed embodiments include computer-implemented systems, apparatuses, and processes that, among other things, automatically generate and populate digital interfaces based on adaptively processed image data captured by a network-connected device operating within a computing environment. For example, an apparatus may receive, from a device, a first signal that includes image data identifying a document associated with a data exchange capable of initiation by the device. The apparatus may detect, within a first portion of the image data, a presence of first textual content associated with a first parameter of the data exchange, extract a first value characterizing the first parameter from the first textual content, and generate and transmit a second signal that includes the first value to the device. The second signal includes information that instructs the device to display the first value within a portion of an interface corresponding to the first parameter. 1. An apparatus , comprising:a communications unit;a storage unit storing instructions; and receive a first signal from a device via the communications unit, the first signal comprising image data that identifies a document, the document being associated with an exchange of data capable of initiation by the device;', 'detect, within a first portion of the image data, a presence of first textual content associated with a first parameter of the data exchange;', 'extract a first value characterizing the first parameter from the first textual content; and', 'generate and transmit, via the communications unit, a second signal that includes the first value to the device, the second signal comprising information that instructs the device to display, using a display unit, the first value within a portion of an interface corresponding to the first parameter., 'at least one processor coupled to the communications unit and the storage unit, the at least one processor being configured to execute the instructions to2. ...

Подробнее
Номер записи: 5
12-01-2017 дата публикации

SYSTEM FOR RECOGNIZING MULTIPLE OBJECT INPUT AND METHOD AND PRODUCT FOR SAME

Номер: US20170011262A1
Автор: ONIS Sebastien
Принадлежит:

Methods, systems, and computer program products are provided for the recognition of input of multiple objects into a computing device, wherein the computing device has a processor and at least one application for recognizing the input under control of the processor. The application is configured to determine at least one geometrical feature of a plurality of elements of the input, and compare the determined at least one geometrical feature with at least one pre-determined geometrical threshold to determine a positive or negative result. If the comparison yields a negative result, the application considers the elements as belonging to one object in the recognition of the input. If the comparison yields a positive result, the application considers the elements as belonging to multiple objects in the recognition of the input. 1. A method of recognizing input of multiple objects to a computing device , the computing device comprising a processor and at least one application for recognizing the input under control of the processor , the method comprising the steps of:determining, with the application, at least one geometrical feature of a plurality of elements of the input;comparing, with the application, the determined at least one geometrical feature with at least one pre-determined geometrical threshold to determine a positive or negative result;if the comparison yields a negative result, considering the elements as belonging to one object in the recognition of the input; andif the comparison yields a positive result, considering the elements as belonging to multiple objects in the recognition of the input.2. A method as claimed in claim 1 , wherein the at least one geometrical feature includes one or more distances between pairs of elements of the plurality of elements.3. A method as claimed in claim 2 , wherein the one or more distances is between one or more factors of the content of each element of each pair of elements.4. A method as claimed in claim 3 , wherein ...

Подробнее
Номер записи: 6
14-01-2016 дата публикации

CHARACTER INPUT APPARATUS AND METHOD BASED ON HANDWRITING

Номер: US20160012285A1
Автор: AHN Yang Keun, JUNG Kwang Mo, KIM Chan Gyu
Принадлежит: KOREA ELECTRONICS TECHNOLOGY INSTITUTE

Provided are a character input apparatus and method based on handwriting. The character input apparatus based on handwriting includes an image obtaining unit configured to obtain an image of a motion of a hand moving in a space, a pattern storage unit configured to store various types of character input pattern information required for inputting characters, a pattern recognizing unit configured to recognize a character input pattern from the image of a motion of a hand obtained by the image obtaining unit, compare the recognized character input pattern with the character input pattern information stored in the pattern storage unit, and output a character matched to the same pattern, and an input character display unit configured to display the character output from the pattern recognizing unit. 1. A character input apparatus based on handwriting , the character input apparatus comprising:an image obtaining unit configured to obtain an image of a motion of a hand moving in a space;a pattern storage unit configured to store various types of character input pattern information required for inputting characters;a pattern recognizing unit configured to recognize a character input pattern from the image of a motion of a hand obtained by the image obtaining unit, compare the recognized character input pattern with the character input pattern information stored in the pattern storage unit, and output a character matched to the same pattern; andan input character display unit configured to display the character output from the pattern recognizing unit.2. The character input apparatus of claim 1 , wherein when the recognized pattern corresponds to a consonant and repeated twice within a predetermined period of time claim 1 , the pattern recognizing unit determines that the pattern corresponds to a pair consonant claim 1 , and outputs a corresponding character.3. The character input apparatus of claim 1 , wherein when the recognized pattern is a vowel and another vowel ...

Подробнее
Номер записи: 7
14-01-2016 дата публикации

ELECTRONIC APPARATUS, METHOD AND STORAGE MEDIUM

Номер: US20160012286A1
Автор: SUGIURA Chikashi
Принадлежит:

According to one embodiment, an electronic apparatus includes a circuitry. The circuitry is configured to input data of an image including a plurality of ruled lines separated by intervals and a plurality of characters. The circuitry is configured to detect a first pair and a second pair of reference ruled lines out of the ruled lines. The circuitry is configured to execute a process for determining the handwritten characters falling within the gap between the first pair of reference ruled lines as one structure, when the characters included in the image fall within a gap between the first pair of reference ruled lines. 1. An electronic apparatus comprising: input data of an image including a plurality of ruled lines separated by intervals and a plurality of characters;', 'detect a first pair and a second pair of reference ruled lines out of the ruled lines;', 'execute a process for determining the handwritten characters falling within the gap between the first pair of reference ruled lines as one structure, when the characters included in the image fall within a gap between the first pair of reference ruled lines; and', 'execute a process for determining a first part of the characters as one structure and a second part of the characters as one structure, when the first part of the plurality of the characters included in the image fall within a gap between the first pair of reference ruled lines and the second part of the plurality of the characters included in the image goes beyond the first pair of reference ruled lines and fall within a gap between the second pair of reference ruled lines., 'circuitry configured to2. The electronic apparatus of claim 1 , whereinthe circuitry is configured to execute a process for obtaining a character recognition result of the handwritten characters in the structure.3. The electronic apparatus of claim 1 , whereinthe circuitry is further configured to determine the first pair and the second pair of reference ruled lines based on ...

Подробнее
Номер записи: 8
14-01-2016 дата публикации

CONTEXT-AWARE HANDWRITING RECOGNITION FOR APPLICATION INPUT FIELDS

Номер: US20160012315A1
Автор: Kelso Scott Edwards, Nicholson John Weldon, Perrin Steven Richard, Zhang Jianbang
Принадлежит:

For context-aware handwriting recognition for input fields, an apparatus, system, method, and computer program product are disclosed. The apparatus may include a processor, a handwriting input unit operatively coupled to the processor, a display operatively coupled to the processor, a field metadata module that obtains metadata related to an input field, a field type module that identifies a field type of the input field associated with the handwriting input based on the metadata, and a recognition tuning module that adjusts a handwriting recognition engine based on the field type. Adjusting the handwriting recognition engine may include increasing a weight given to text having particular characteristics, based on the field type. Obtaining the metadata related to an input field may include querying an application for properties of the input field and/or identifying text adjacent to the input field. 1. An apparatus comprising:a processor;a handwriting input unit operatively coupled to the processor that receives a handwriting input;a field metadata module that obtains metadata related to an input field associated with the handwriting input;a field type module that identifies a field type of the input field based on the metadata; anda recognition tuning module that adjusts a handwriting recognition engine based on the field type.2. The apparatus of claim 1 , further comprising a field property module that queries an application for properties of the input field and provides results of the query as metadata to the field metadata module.3. The apparatus of claim 1 , further comprising a field text module that identifies text adjacent to the input field and provides the text as metadata to the field metadata module.4. The apparatus of claim 1 , further comprising an association module that associates the handwriting input with a particular input field based on a field type of the particular input field and content of the handwriting input.5. The apparatus of claim 4 , ...

Подробнее
Номер записи: 9
14-01-2021 дата публикации

ELECTRONIC DEVICE AND CONTROL METHOD THEREOF

Номер: US20210012101A1
Автор: BOKHAN Kostiantyn, KHOMENKO Viacheslav, OSADCHIY Vadym, RADYVONENKO Olga, Viatchaninov Oleksandr
Принадлежит: SAMSUNG ELECTRONICS CO., LTD.

An electronic device is disclosed. The electronic device comprises a storage unit for storing a training model of a multi-dimensional long short-term memory (MDLSTM), and a processor for acquiring an image including at least one of handwritten text and printed text, identifying each text line region in the image through image processing, and recognizing text included in the each identified text line region, on the basis of the training model. 1. An electronic apparatus comprising:a storage configured to store a training model of multi-dimensional long short-term memory (MDLSTM); anda processor configured to acquire an image including at least one of handwritten text and printed text, identify each of text line regions in the image through image processing, and recognize text included in the each identified text line region based on the training model.2. The apparatus of claim 1 , wherein the processor is configured to binarize text region in the image and perform the image processing by correction processing with respect to the binarized text region.3. The apparatus of claim 2 , wherein the correction processing includes at least one of removal of a slope claim 2 , height standardization and skeletonization with respect to the text region.4. The apparatus of claim 1 , wherein the processor is configured to identify a region including the identified text line as a plurality of vertical blocks claim 1 , and calculate a probability of a character estimated from each of the vertical blocks based on a pixel value of each vertical block.5. The apparatus of claim 4 , wherein the processor is configured to combine an existence probability of a first character in a first vertical block claim 4 , an absence probability of the first character in the first vertical block claim 4 , an existence probability of a second character in a second vertical block claim 4 , and an absence probability of the second character in the second vertical block to calculate a plurality of ...

Подробнее
Номер записи: 10
10-01-2019 дата публикации

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM

Номер: US20190012716A1
Автор: MURAKAMI Takuya
Принадлежит: RAKUTEN, INC.

The present invention aims to provide an information processing device, an information processing method, and the like capable of reducing labor of associating an item for sale with a category. The information processing device acquires an image specified by a user. The information processing device extracts a feature value of the specified image. The information processing device acquires category information corresponding to an item for sale represented by the specified image. The information processing device searches for images similar to the specified image, based on the extracted feature value. The information processing device causes at least one of the found images to be displayed as a search result. The information processing device, when the user has selected any one image from the displayed search result, makes a storage unit store the acquired category information in association with sale item identification information corresponding to the selected image. 110-. (canceled)11. An information processing device comprising:at least on memory configured to store computer program code;at least one processor configured to read said computer program code and operate as instructed by said computer program code, said computer program code including:image acquisition code configured to cause at least one of said at least one processor to acquire a first image drawn by a user;extraction code configured to cause at least one of said at least one processor to extract a first feature value of the first drawn image;category information acquisition code configured to cause at least one of said at least one processor to acquire category information indicating a category corresponding to an item for sale represented by the first drawn image among a plurality of categories for classifying items for sale;search code configured to cause at least one of said at least one processor to search for first item images similar to the first drawn image, based on the first extracted ...

Подробнее
Номер записи: 11
19-01-2017 дата публикации

MULTI-SCRIPT HANDWRITING RECOGNITION USING A UNIVERSAL RECOGNIZER

Номер: US20170017835A1
Автор: Bellegarda Jerome R., DIXON Ryan S., DOLFING Jannes G. A., GROETHE Karl M.
Принадлежит:

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed. 1. A non-transitory computer-readable media having instructions stored thereon , the instructions , when executed by one or more processors , cause the processors to perform operations comprising:training a multi-script handwriting recognition model based on spatially-derived features of a multi-script training corpus, the multi-script training corpus including respective handwriting samples corresponding to characters of one or more scripts; andproviding real-time handwriting recognition for a user's handwriting input using the multi-script handwriting recognition model that has been trained on the spatially-derived features of the multi-script training corpus.2. The media of claim 1 , wherein the spatially-derived features of the multi-script training corpus are stroke-order independent and stroke-direction independent.3. The media of claim 1 , wherein the training of the multi-script handwriting recognition model is independent of temporal information associated with respective strokes in the handwriting samples.4. The media of claim 1 , wherein the one or more scripts include one or more Chinese characters claim 1 , emoji characters claim 1 , and Latin script.5. The media of claim 1 , wherein the one or more scripts include one or more Chinese characters claim 1 , Arabic script claim 1 , and Latin script.6. The media of claim 1 , wherein the one or more scripts include one or more non-overlapping scripts defined by the ...

Подробнее
Номер записи: 12
19-01-2017 дата публикации

PICTORAL METHODS FOR APPLICATION SELECTION AND ACTIVATION

Номер: US20170018100A1
Автор: YEE Mong Suan
Принадлежит:

Methods and devices provide a quick and intuitive method to launch a specific application, dial a number or send a message by drawing a pictorial key, symbol or shape on a computing device touchscreen, touchpad or other touchsurface. A shape drawn on a touchsurface is compared to one or more code shapes stored in memory to determine if there is a match or correlation. If the entered shape correlates to a stored code shape, an application, file, function or keystroke sequence linked to the correlated code shape is implemented. The methods also enable communication involving sending a shape or parameters defining a shape from one computing device to another where the shape is compared to code shapes in memory of the receiving computing device. If the received shape correlates to a stored code shape, an application, file, function or keystroke sequence linked to the correlated code shape is implemented. 147-. (canceled)48. A method for initiating actions on a computing device , comprising:receiving on a touchsurface a series of movements and touches as a received shape; wherein the stored code shape comprises one or more parameters defining a nominal shape representative of a plurality of received shapes, each of the plurality of received shapes comprising a series of one or more movements and touches defining the received shape, and a variability of the plurality of received shapes about the nominal shape, and', 'wherein comparing the received shape to the code shape stored in the memory comprises determining whether the received shape correlates to the nominal shape within the determined variability; and, 'comparing the received shape to a code shape stored in memory,'}implementing an action linked to the stored code shape when the received shape correlates to the code shape, wherein the code shape stored in the memory is linked to at least one action.49. The method of claim 48 , wherein the touchsurface is one of a touchscreen and a touchpad.50. The method of claim ...

Подробнее
Номер записи: 13
17-01-2019 дата публикации

CONVERTING WHITEBOARD IMAGES TO PERSONALIZED WIREFRAMES

Номер: US20190018660A1
Автор: Ananthapur Bache Vijay Kumar, Bera Jhilam, Ekambaram Vijay, Sadacharam Saravanan
Принадлежит:

A method for creating a wireframe model for a user interface. A computer identifies an image on a user interface. The computer performs image recognition to identify objects and text within the image. The computer creates a digital widget model based on the step of performing image recognition. The computer delivers digital widget output to a user experience designer for editing, wherein the digital widget output is based on the step of creating. The computer stores edits made by the user experience designer in a historical records database and the wireframe model design is finalized. 1. A method for creating a wireframe model for a user interface , comprising:identifying, by a computer, an image created on a user interface;performing, by the computer, image recognition to identify objects and text within said image;creating, by the computer, a digital widget model based on said step of performing image recognition;delivering, by the computer, digital widget output to a user experience designer for editing, said digital widget output based on said step of creating;storing, by the computer, edits made by said user experience designer in an historical record database;finalizing a final wireframe model design.2. The method of claim 1 , wherein said creating said digital widget includes comparing claim 1 , by the computer claim 1 , said digital widget model to said historical record database claim 1 , said comparing includes a step of cognitive analysis to recognize similarities between said digital widget model and previously-created features stored in said historical record database.3. The method of claim 1 , wherein said historical record database includes HMI guidelines and previous wireframe objects created by said user experience designer.4. The method of claim 1 , further comprising:comparing said digital widget modal to standardized HMI guidelines for creation of a wireframe model.5. The method of claim 4 , further comprising:replacing guideline-rejected objects ...

Подробнее
Номер записи: 14
26-01-2017 дата публикации

INFORMATION PROCESSING SYSTEM AND INFORMATION PROCESSING METHOD THEREOF

Номер: US20170024417A1
Автор: LEE Myeong Hwan, SONG Tae Min
Принадлежит:

An information processing system for a handwriting search according to an embodiment of the present invention comprises: an information extraction device for transforming pattern information sensed by an electronic pen into handwriting data on a recording medium with a pattern formed thereon; and an information management device for transforming the handwriting data into digital data, storing the handwriting data and the digital data, searching for digital data including a keyword when a search request including the keyword is received from a user terminal, and transmitting, to the user terminal, the handwriting data corresponding to the searched digital data. 1. An information processing system for a handwriting search , the information processing system comprising:an information extraction device configured to transform pattern information detected by an electronic pen from a recording medium with a pattern formed thereon into handwriting data; andan information management device configured to transform the handwriting data into digital data, store the handwriting data and the digital data, search for digital data including a keyword when a search request including the keyword is received from a user terminal, and transmit handwriting data corresponding to the found digital data to the user terminal.2. The information processing system of claim 1 , wherein the handwriting data includes handwriting recorded on the recording medium by the electronic pen claim 1 , and the digital data includes a digital font transformed from the handwriting.3. The information processing system of claim 2 , wherein the digital font includes a keyword transformed from the handwriting.4. The information processing system of claim 2 , wherein the information management device includes:a digital data conversion unit configured to transform handwriting data received from the information extraction device into digital data;a storage unit configured to store the handwriting data and the ...

Подробнее
Номер записи: 15
26-01-2017 дата публикации

CAPTCHA TECHNIQUES UTILIZING TRACEABLE IMAGES

Номер: US20170024556A1
Автор: Akula Nagasravani, Mohamad Abdul Mohamad Raja Gani, Raj Rachit
Принадлежит:

Techniques are disclosed for generating, utilizing, and validating traceable image CAPTCHAs. In certain embodiments, a traceable image is displayed, and a trace of the image is analyzed to determine whether a user providing the trace is human. In certain embodiments, a computing device receives a request for an image, and in response, creates a traceable image based upon a plurality of image elements. The computing device transmits data representing the traceable image to cause a second computing device to display the traceable image via a touch-enabled display. The computing device receives a user trace input data generated responsive to a trace made at the second computing device, and determines whether the trace is within an error tolerance range of the set of coordinates associated with the traceable image. The computing device then sends a result of the determination. 120.-. (canceled)21. A system comprising:one or more processors; selecting a first image element from a plurality of image elements, the first image element having a first set of points;', 'selecting a second image element from the plurality of image elements, the second image element having a second set of points;', 'creating, by a first computing device, a traceable image by aligning the first image element with the second image element, wherein aligning the first image element with the second image element includes connecting an end point in the first set of points in the first image element with another end point in the second set of points in the second image element;', 'sending, by the first computing device, data representing the traceable image to be displayed by a second computing device;', 'receiving input data corresponding to a trace of the displayed traceable image made at the second computing device;', 'determining, based upon the received input data, whether the trace of the displayed traceable image is within an error tolerance range of a set of coordinates associated with the ...

Подробнее
Номер записи: 16
25-01-2018 дата публикации

HANDWRITING RECOGNITION METHOD AND APPARATUS

Номер: US20180025248A1
Автор: CHEN Youxin, LIU Chuanxia, SHAN Yuxian
Принадлежит:

A method of generating handwriting information about handwriting of a user includes determining a first writing focus and a second writing focus; sequentially shooting a first local writing area, which is within a predetermined range from a first writing focus, and a second local writing area, which is within a predetermined range from a second writing focus; obtaining first handwriting from the first local writing area and second handwriting from the second local writing area; combining the first handwriting with the second handwriting; and generating the handwriting information, based on a result of the combining. 1. A device for generating handwriting information about handwriting of a user , the device comprising:a user interface configured to receive a user input;a signal obtainer configured to sequentially shoot a first local writing area, which is within a predetermined range from a first writing focus, and a second local writing area, which is within a predetermined range from a second writing focus; anda controller configured to determine the first writing focus and the second writing focus, obtain first handwriting from the first local writing area, obtain second handwriting from the second local writing area, combine the first handwriting with the second handwriting, and generate handwriting information, based on a result of the combining.2. The device of claim 1 , whereinthe signal obtainer traces a visual focus of the user, andthe controller determines the first writing focus and the second writing focus, based on the traced visual focus.3. The device of claim 1 , whereinthe user interface receives information about a color of handwriting from the user, andthe controller obtains the first handwriting from the first local writing area and the second handwriting from the second local writing area, based on information about the color of the handwriting.4. The device of claim 1 , wherein the controller compares the first handwriting with the second ...

Подробнее
Номер записи: 17
04-02-2016 дата публикации

HANDWRITING INPUT SYSTEM AND HANDWRITING INPUT METHOD

Номер: US20160034752A1
Автор: TUNG YU-TENG
Принадлежит:

A handwriting input system includes a handwriting pen, a handwriting plate and a processing unit. The handwriting pen includes a pen body, a first sensing unit and a first communication unit. The first sensing unit senses an action of the pen body to generate a sensing data. The handwriting plate includes a touch unit, a display unit and a second communication unit. The touch unit senses a contact trajectory and a contact time while the handwriting pen contacts the handwriting plate. The processing unit is selectively disposed in one of the handwriting pen and the handwriting plate. The processing unit calculates a tilt angle of the pen body according to the sensing data, determines a contact shape according to the tilt angle, determines an ink output amount according to the contact time, and determines a handwriting image according to the contact trajectory, the contact shape and the ink output amount. 1. A handwriting input system comprising:a handwriting pen comprising a pen body, a first sensing unit and a first communication unit, the first sensing unit and the first communication unit being disposed in the pen body, the first sensing unit sensing an action of the pen body to generate a sensing data;a handwriting plate comprising a touch unit, a display unit and a second communication unit, the touch unit sensing a contact trajectory and a contact time while the handwriting pen contacts the handwriting plate, the first communication unit communicating with the second communication unit; anda processing unit selectively disposed in one of the handwriting pen and the handwriting plate, the processing unit calculating a tilt angle of the pen body according to the sensing data, determining a contact shape according to the tilt angle, determining an ink output amount according to the contact time, and determining a handwriting image according to the contact trajectory, the contact shape and the ink output amount, and the display unit displaying the handwriting image ...

Подробнее
Номер записи: 18
02-02-2017 дата публикации

PROVIDING DRAWING ASSISTANCE USING FEATURE DETECTION AND SEMANTIC LABELING

Номер: US20170032690A1
Автор: Hertzmann Aaron Phillip, Li Wilmot Wei-Mau, Winnemoeller Holger, Xie Jun
Принадлежит:

Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines. 1. A method of using semantic labeling to provide drawing assistance to a user sketching an image comprising:generating, by one or more processors, a guidance map for the image, the guidance map including feature labels identifying one or more portions of the guidance map corresponding to one or more features of the image;detecting a stroke drawn by a user;associating a feature label with the stroke;identifying a portion of the guidance map nearest to the stroke that has an associated feature label that matches the feature label of the stroke; andgenerating, by the one or more processors, a geometrically-corrected stroke using the identified portion of the guidance map nearest to the stroke that has the associated feature label that matches the feature label of the stroke.2. The method as recited in claim 1 , wherein generating the guidance map comprises generating an edge guidance map by applying an edge detection filter to the image.3. The method as recited in claim 2 , wherein generating the guidance map further comprises:applying a feature detection algorithm to the image to identify one or more features in the image; andassociating feature labels with edges in the edge guidance map corresponding to the identified features.4. The method as recited in claim 2 , wherein generating the guidance map ...

Подробнее
Номер записи: 19
01-05-2014 дата публикации

Character recognition apparatus, character recognition method, and computer-readable medium

Номер: US20140119641A1
Автор: Hideto Oda
Принадлежит: Fuji Xerox Co Ltd

A character recognition apparatus includes an extracting unit extracting a feature point for a line in a handwritten character, first and second generation units, a learning unit, and a determination unit. The first generation unit generates first feature data from feature points for lines including an in-same-character line (first line) and being selected from lines in character-code-specified handwritten characters (known lines). The second generation unit generates second feature data from feature points for lines including an after-character-transition line (second line) and being selected from known lines. The learning unit causes a discriminator to learn classifications for first and second lines based on the first and second feature data. The determination unit determines whether each line in character-code-unknown handwritten characters is a first or second line, based on which classification is determined by the discriminator for feature data for the line.

Подробнее
Номер записи: 20
04-02-2021 дата публикации

ULTRASOUND BASED AIR-WRITING SYSTEM AND METHOD

Номер: US20210033693A1
Автор: AHMED Tarig Ballal Khidir, AL-NAFFOURI TAREQ YOUSEF, Chen Hui
Принадлежит:

A method for motion tracking and text recognition, the method including a step of generating ultrasound waves with a transmitter; a step of receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves; a step of estimating with a processor, angle-of-arrival information for the ultrasound waves; a step of associating the angle-of-arrival information with a gesture; a step of extracting features from the gesture; and a step of classifying the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates. 1. A method for motion tracking and text recognition , the method comprising:generating ultrasound waves with a transmitter;receiving the ultrasound waves at a receiver, the receiver including sensors that record the ultrasound waves;estimating with a processor, angle-of-arrival information for the ultrasound waves;associating the angle-of-arrival information with a gesture;extracting features from the gesture; andclassifying the gesture as a specific text character based on the extracted features by comparing the extracted features with known text characters stored in one or more templates.2. The method of claim 1 , wherein the gesture is associated with movement of a user claim 1 , the gesture causing the transmitter to generate the ultrasound waves.3. The method of claim 1 , wherein the classifying includes redundant dictionary matching in which at least one of the one or more templates is extended based on shift and shrink to fit users with different writing speed or different writing style.4. The method of claim 3 , wherein the redundant dictionary matching includes a decision tree that is performed on at least one pair of text characters that is determined to have a similar branch.5. The method of claim 1 , wherein the classifying includes dynamic time warping in which the extracted features are compared with the ...

Подробнее
Номер записи: 21
04-02-2021 дата публикации

SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION

Номер: US20210034849A1
Автор: BROCKLER Frank, HUTKOWSKI Paul, PTUCHA Raymond, SUCH Felipe Petroski
Принадлежит: KODAK ALARIS INC.

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block. 1. A system , comprising:at least one processor; and receive a digitized object, the digitized object corresponding to an image including at least one symbol;', 'form digitized line blocks from the digitized object by determining whitespace separators in the digitized object;', 'transform the line blocks into one or more word blocks separated by whitespace, the one or more word blocks having a value associated with at least one symbol forming the one or more word blocks;', 'resize each word block of the one or more word blocks into a canonical representation of a fixed height;', 'evaluate each word block of the one or more word blocks with a dictionary, the dictionary containing a collection of common words;', 'output a first word prediction when one or more of the word blocks corresponds to a word in the collection;', 'assign one or more descriptors to the one or more word blocks when the one more word blocks do not correspond to the collection;', 'perform probabilistic correction on the one or more word blocks; and', 'output a second word prediction, the second word prediction corresponding to the value of the word block., 'memory including instructions that, when executed by the at least ...

Подробнее
Номер записи: 22
04-02-2021 дата публикации

SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION

Номер: US20210034850A1
Автор: BROCKLER Frank, HUTKOWSKI Paul, PTUCHA Raymond, SUCH Felipe Petroski
Принадлежит: KODAK ALARIS INC.

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block. 1. A non-transitory computer-readable storage medium storing instructions that , when executed by at least one processor of a computing device , cause the computing device to:receive a digital image corresponding to a word block, the word block containing at least one symbol corresponding to a letter, number, character, or a combination thereof;evaluate the word block with a first neural network, the first neural network assigning at least one of a descriptor or a steering factor to the word block;process the word block with a second neural network, the second neural network evaluating the at least one of the descriptor or the steering factor to prioritize evaluation;combine a first output from the first neural network and a second output from the second neural network; andoutput a predicted word corresponding to a value of the word block.2. The non-transitory computer readable storage medium of claim 1 , wherein the instructions claim 1 , when executed claim 1 , further cause the computing device to:resize the word block, the resized word block based on at least one of a height or a width of the word block;predict a number of symbols and blanks in the word block; andperform probabilistic ...

Подробнее
Номер записи: 23
24-02-2022 дата публикации

METHOD AND APPARATUS FOR AUGMENTED REALITY

Номер: US20220058879A1
Автор: ROHAN Devesh
Принадлежит:

The disclosure provides an augmented reality system () including an input unit (), a text recognition unit (), a natural language processing unit (), a positioning unit (), and an output unit (). The input unit () captures an image. The text recognition unit () identifies an information on a surface depicted in the image and generates an input data based on the information. The natural language processing unit ( ) determines a context of the input data and generates at least one assistive information based on the context. The positioning unit () determines one or more spatial attributes based on the image and generates a positioning information based on the spatial attributes. The output unit () displays the assistive information based on the positioning information. 1. An electronic device in augmented reality system , the electronic device comprising:an input unit configured to capture an image;{'claim-text': ['identify, from the image, an information on a surface depicted in the image, and', 'generate an input data based on the information;'], '#text': 'a text recognition unit configured to:'}{'claim-text': ['determine a context of the input data, and', 'generate at least one assistive information based on the context;'], '#text': 'a natural language processing unit configured to:'}{'claim-text': ['determine one or more spatial attributes based on the image, and', 'generate a positioning information based on the spatial attributes; and'], '#text': 'a positioning unit configured to:'}{'claim-text': 'display the assistive information based on the positioning information.', '#text': 'an output unit configured to:'}2. The electronic device of claim 1 , wherein the spatial attributes include at least one of:an angle between the augmented reality system and the surface,a distance between the augmented reality system and the surface, oran obstruction in a field of view between the augmented reality system and the surface.3. The electronic device of claim 2 , wherein the ...

Подробнее
Номер записи: 24
18-02-2021 дата публикации

METHOD AND SYSTEM FOR SENTIMENT ANALYSIS OF INFORMATION

Номер: US20210049197A1
Автор: Xia Wei, Yi Zheng
Принадлежит: Hithink Royalflush Information Network Co., Ltd.

One aspect of the present disclosure relates to a method of sentiment analysis based on ambiguity analysis, which includes analyzing information with the sentiment analysis models and the ambiguity analysis models. Another aspect of the present disclosure relates to a method of training the sentiment analysis models and ambiguity analysis models, which includes acquiring information, constructing lexicons, conducting sentiment analysis and ambiguity analysis with said lexicons, acquiring corpus, and training models, etc. Meanwhile, another aspect of the present disclosure relates to a system of sentiment analysis, which includes input, and output modules, acquisition modules, processing modules and database. 1. A device , comprising:a non-transitory computer readable storage medium storing executable instructions; andat least one processor in communication with the non-transitory computer readable storage medium, wherein when executing the executable instructions, the at least one processor is configured to cause the device to:obtain a user input via an interface of the device, wherein the interface includes a conversational interface;send, over a network, the user input to a system;receive, over the network from the system, non-ambiguous information obtained based on an ambiguity analysis performed by the system on information retrieved based on the user input, the non-ambiguous information containing the user input; anddisplay the non-ambiguous information on the interface of the device.2. The device of claim 1 , wherein the ambiguity analysis performed by the system on the information comprises:constructing a keyword lexicon by retrieving terminologies from the information and storing the terminologies in the keyword lexicon; andconducting the ambiguity analysis of the information based on the keyword lexicon.3. The device of claim 2 , wherein the conducting the ambiguity analysis of the information based on the keyword lexicon comprises:constructing a repository ...

Подробнее
Номер записи: 25
03-03-2022 дата публикации

DISPLAY APPARATUS, DISPLAY METHOD, MEDIUM, AND DISPLAY SYSTEM

Номер: US20220066728A1
Автор: OSHIMA Yoshiaki
Принадлежит:

A display apparatus that displays handwritten data includes a display, a memory, and a processor configured to execute receiving as input the handwritten data; detecting one or more secondary display apparatuses; displaying, in a case where the one or more secondary display apparatuses are detected by the detecting, on the display of the display apparatus, an operation command related to a function of displaying data by using the display apparatus and the one or more secondary display apparatuses, based on the handwritten data received by the receiving; and predetermined processing related to the function, in response to receiving an operation performed by a user with respect to the operation command.

Подробнее
Номер записи: 26
23-02-2017 дата публикации

HANDWRITING RECOGNITION WITH NATURAL USER INPUT ON MULTITOUCH SURFACES

Номер: US20170053161A1
Автор: Bosnic, Harden Derek M., JR. Cameron J.
Принадлежит:

The method includes receiving, by one or more computer processors, data indicating a hand is on a touch-sensitive surface. The method further includes identifying, by one or more computer processors, a position of the hand. The method further includes determining, by one or more computer processors, a change in the position of the hand. The method further includes characterizing, by one or more computer processors, the change in position of the hand on the touch-sensitive surface. The method further includes generating, by one or more computer processors, an alphanumeric character based upon the characterized change in the position of the hand. 1. A method for character identification on a multi-touch surface , the method comprising:presenting, by one or more computer processors, a list of a plurality of general classifiers, and, in response to a user selecting one or more general classifiers from the list of the plurality of general classifiers, storing, by one or more computer processors, the one or more general classifiers in a profile associated with the user;receiving, by one or more computer processors, data indicating a hand is on a touch-sensitive surface;identifying, by one or more computer processors, a position of the hand;determining, by one or more computer processors, a change in the position of the hand;identifying, by one or more computer processors, the one or more general classifiers from the profile;identifying, by one or more computer processors, one or more specific classifiers from a plurality of specific classifiers based, at least in part, on a training phase;modifying, by one or more computer processors, an algorithm based, at least in part, on the identified one or more general classifiers and the identified one or more specific classifiers;the modified algorithm analyzing, by one or more computer processors, the change in the position of the hand;the modified algorithm generating, by one or more computer processors, a list of characters ...

Подробнее
Номер записи: 27
21-02-2019 дата публикации

STROKE EXTRACTION IN FREE SPACE

Номер: US20190057266A1
Автор: Dow Eli M., Fitzsimmons Thomas D., Garrett Tynan J., Metruck Emily M.
Принадлежит:

An approach for extracting strokes in a free space environment is described. Boundaries are displayed in a free space environment describing at least one two-dimensional surface area. One or more language movements are extracted from the free space environment by a paired ring device and transmitted as images for processing. Haptic feedback is provided to the paired ring device in response to detecting at least one language movement occurring outside of at least one two-dimensional surface area. At least one extracted language movement is input into a character training model. 1. A method for stroke extraction in free space utilizing a paired ring device and a paired display device connected to the paired display device , the method comprising:displaying, by one or more computer processors, on the paired display device, a modified free space environment including one or more bounded surface areas, with the bounded surface areas including an area of two-dimensional space framed by a boundary within the free space environment;receiving, by the one or more computer processors, one or more images transmitted from the paired ring device, wherein the one or more images are transcribed sequentially from one or more language movements recorded by the paired ring device utilizing a magnitude value and a direction value of proper acceleration of the one or more language movements, and wherein the one or more images include one or more of a plurality of vector points, a plurality of coordinates, and a plurality of dots interconnected by a plurality of lines;determining, by the one or more processors, at least one of the one or more language movements crossed at least one side of at least one bounded surface area of the one or more bounded surface areas;responsive to determining that at least one of the one or more language movements crossed at least one side of at least one bounded surface area of the one or more bounded surface areas, providing, by the one or more processors, ...

Подробнее
Номер записи: 28
03-03-2016 дата публикации

SYSTEM AND METHOD FOR TRANSCRIBING HISTORICAL RECORDS INTO DIGITIZED TEXT

Номер: US20160063321A1
Автор: Brown Laryn, Murdock Michael, Reese Jack, Reid Shawn
Принадлежит: Ancestry.com Operations Inc.

A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors. 1. A method for creating digitized text for a record from an image of the record , comprising:obtaining one or more digital images of a record;evaluating the digital images in order to locate each of multiple word images;for each located word image, identifying multiple word features of that word image;assigning, to one group of word images, designated ones of the multiple word images based on the distance between the multiple word images, the distance representing the similarity of word features between at least two of the word images;selecting a representative word image in the one group of word images;selecting digitized text for the representative word image; andassigning the selected digitized text to each of the word images in the one group of word images.2. The method of claim 1 , wherein the record is a historical record having handwritten words claim 1 , and wherein the multiple word images are each an image of one of the handwritten words.3. The method of claim ...

Подробнее
Номер записи: 29
03-03-2016 дата публикации

System and method for transcribing handwritten records using word grouping with assigned centroids

Номер: US20160063355A1
Автор: Jack Reese, Laryn Brown, Michael Murdock, Shawn Reid
Принадлежит: Ancestry com Inc

A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

Подробнее
Номер записи: 30
01-03-2018 дата публикации

DETECTING ARROWS WITHIN IMAGES

Номер: US20180060654A1
Автор: Hightower Ron
Принадлежит: KONICA MINOLTA LABORATORY U.S.A., INC.

A method for processing an image with a processor, including: identifying, within an image, a candidate arrow including a long path adjacent to a plurality of short paths; determining a direction of the candidate arrow based on the long path; estimating a tip pixel within the plurality of short paths based on the direction of the candidate arrow; determining, for the candidate arrow, a plurality of arrowhead edges in the plurality of short paths based on the tip pixel; and generating, for the candidate arrow, a plurality of refined arrowhead edges based on the plurality of arrowhead edges, the direction, and the tip pixel. 1. A method for processing an image with a processor , comprising:identifying, within an image, a candidate arrow comprising a long path adjacent to a plurality of short paths;determining a direction of the candidate arrow based on the long path;estimating a tip pixel within the plurality of short paths based on the direction of the candidate arrow;determining, for the candidate arrow, a plurality of arrowhead edges in the plurality of short paths based on the tip pixel; andgenerating, for the candidate arrow, a plurality of refined arrowhead edges based on the plurality of arrowhead edges, the direction, and the tip pixel.2. The method of claim 1 , wherein determining the direction of the candidate arrow comprises:calculating a direction vector based on a starting endpoint of the long path and a terminal endpoint of the long path.3. The method of claim 2 , wherein estimating the tip pixel comprises:generating a plurality of test vectors based on the terminal endpoint and a plurality of pixels within the plurality of short paths;calculating a plurality of dot products between the direction vector and the plurality of test vectors; andidentifying a test vector associated with the maximum dot product of the plurality of dot products,wherein the tip pixel is the pixel of the plurality of pixels corresponding to the test vector associated with the ...

Подробнее
Номер записи: 31
02-03-2017 дата публикации

SYSTEM AND METHOD OF DIGITAL NOTE TAKING

Номер: US20170060821A1
Автор: BLESTEL Lionel, BOEKHOORN Arnoud, BOURLIEUX François, COULON Cédric, DELBECQUE Nathalie, LAVAL Aristote, LELORE Thibault, MéLINAND Robin, NZIENGUI MOUBAMBA Maixent, PATRY Olivier, PENIN Thomas, Rucine Nicolas
Принадлежит:

A system, method and computer program product for use in digital note taking with handwriting input to a computing device are provided. The computing device is connected to an input device, or an input surface. A user provides input by applying pressure to or gesturing above the input surface using a finger or an instrument. The present system and method monitors the input strokes. The computing device includes a processor controlling an application for recognizing the handwriting input. The system application causes display of, on a display interface, a guide element for handwriting input and digital ink in a block layout in accordance with a layout of blocks of the handwriting input and a configuration of the computing device display interface. The guide element is displayed based on the digital ink block content and layout and typeset ink block content and layout formed from the recognized handwriting input. 1. A system for digital note taking on computing devices , each computing device comprising a processor and at least one non-transitory computer readable medium for recognizing handwriting note taking input under control of the processor , the at least one non-transitory computer readable medium configured to:cause display of, on a display interface of a computing device, a guide element for handwriting input; andcause display of, on the display interface, digital ink in a block layout in accordance with a layout of blocks of the handwriting input and a configuration of the computing device display interface,wherein the guide element is displayed based on the digital ink block content and layout and typeset ink block content and layout formed from the recognized handwriting input.2. A system according to claim 1 , wherein the guide element comprises a plurality of substantially parallel lines displayed on the display interface.3. A system according to claim 2 , wherein the displayed spacing between each of the plurality of substantially parallel lines is ...

Подробнее
Номер записи: 32
02-03-2017 дата публикации

ORGANIZING WRITTEN NOTES USING CONTEXTUAL DATA

Номер: US20170061206A1
Автор: Black David Robert, Halle Brett Reed
Принадлежит:

A system and a method are disclosed for organizing content collected in a pen-based computing system. Content collected in the pen-based computing system includes stroke data collected by a smart pen as well as other contextual data collected by the pen-based computing system. The collected stroke data includes timestamps and positional data. Based on correlations of spatial and temporal data, collected stroke data is grouped into clusters of stroke data. The clusters of stroke data, along with contextual data, are further grouped into snippets based on temporal correlations. 1. A method for organizing content collected in a pen-based computing system , the method comprising:obtaining a plurality of clusters of stroke data, the stroke data comprising representations of strokes made by a smart pen with respect to a writing surface, each cluster having an associated timestamp based on timing of the strokes made by the smart pen;obtaining one or more contextual data items having one or more associated timestamps based on a timing of when the contextual data items were captured by a computing system of the pen-based computing system;grouping, by a processor, the obtained plurality of clusters and the obtained one or more contextual data items into one or more snippets based on a temporal proximity of the timestamps associated with the obtained clusters and the timestamps associated with the contextual data items; andoutputting a representation of the one or more snippets.2. The method of claim 1 , further comprising:receiving, from a user of the pen-based computing system, a correction to the one or more snippets;responsive to receiving the correction, adjusting a grouping of the plurality of clusters and the one or more contextual data items into the one or more snippets; andoutputting a representation of the corrected snippets.3. The method of claim 1 , further comprising storing claim 1 , in the pen-based computing system claim 1 , the one or more snippets.4. The ...

Подробнее
Номер записи: 33
02-03-2017 дата публикации

SYSTEM AND METHOD FOR SUPERIMPOSED HANDWRITING RECOGNITION TECHNOLOGY

Номер: US20170061223A1
Автор: LALLICAN Pierre-Michel, PERRAUD Freddy, WIMMER Zsolt
Принадлежит:

A system and method is able to recognize a user's natural superimposed handwriting without any explicit separation between characters. The system and method is able to process single-stroke and multi-stroke characters. The system and method can also process cursive handwriting. Further, the system and method can determine the boundaries of input words either by the use of a specific user input gesture or by detecting the word boundaries based on language characteristics and properties. The system and method analyzes the handwriting input through the processes of segmentation, character recognition, and language modeling. These three processes occur concurrently through the use of dynamic programming. 1. A non-transitory computer readable medium having a computer readable program code embodied therein , said computer readable program code adapted to be executed to implement a method for providing handwriting recognition for superimposed stroke input , said method comprising:creating, with a segmentation expert, a segmentation graph based on a plurality of input strokes, at least two of the strokes being at least partially superimposed on one another, wherein the segmentation graph consists of nodes and paths corresponding to character hypotheses formed by segmenting the input strokes to take into account the at least partially superimposed strokes;assigning, with a recognition expert, a recognition score to each node of the segmentation graph based on language recognition information;generating, with a language expert, linguistic meaning of the input strokes by optimizing the recognition scores of the node paths of the segmentation graph based on a language model; andproviding an output based on the collaborative analysis of the segmentation graph, the recognition score, and the language model by the segmentation, recognition and language experts.2. A non-transitory computer readable medium according to claim 1 , wherein the input stroke is preprocessed claim 1 , ...

Подробнее
Номер записи: 34
17-03-2022 дата публикации

MANAGING REAL-TIME HANDWRITING RECOGNITION

Номер: US20220083216A1
Автор: Bellegarda Jerome R., DIXON Ryan S., DOLFING Jannes G., GROETHE Karl M., MEIER Ueli, Misra Karan, XIA Mei-Qun
Принадлежит:

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed. 1. An electronic device , comprising:a display;a touch-sensitive surface;one or more processors; andmemory storing one or more programs configured to be executed by the one or more processors, receiving a handwriting input, the handwriting input comprising a plurality of handwritten strokes provided on a touch-sensitive surface coupled to the device;', 'displaying the plurality of handwritten strokes in a handwriting input area of a handwriting input interface;', 'segmenting the plurality of handwritten strokes into two or more recognition units, each recognition unit comprising a respective subset of the plurality of handwritten strokes;', 'receiving an edit request;', 'in response to the edit request, visually distinguishing at least one of the two or more recognition units in the handwriting input area; and', 'detecting a predetermined deletion gesture input over the at least one of the of the two or more recognition units in the handwriting input area; and', 'in response to the detecting the predetermined deletion gesture input, removing the respective subset of handwritten strokes corresponding to the at least one of the of the two or more recognition units in the handwriting input area., 'the one or more ...

Подробнее
Номер записи: 35
10-03-2016 дата публикации

ELECTRONIC CUSTODY AND CONTROL SYSTEM FOR HUMAN ASSAY TEST SAMPLES

Номер: US20160070865A1
Автор: Lappe Murray, Rein Brad
Принадлежит:

A system, method, and computer program that may used to more quickly, accurately, and efficiently identify, catalog, and track human assay samples and create documentation with respect to the human assay samples. The computer program and method include the steps of: storing donor information in a donor information database accessible by a computer; storing client information in a client information database accessible by the computer; retrieving client information necessary to determine a type of test to be performed on a specimen; storing collection facility information in a collection facility database accessible by the computer; administering a human analyte test using the computer program to guide a collector of the specimen and identify problematic exceptions; receiving the test result electronically and storing the result in a test result database accessible by the computer; and permitting the client, Medical Review Officer, and other authorized persons to electronically access the test result via a communications network. 1an electronic testing device for testing the human analyte specimen provided by the donor;an electronic signature reader for receiving a handwritten signature from the donor and converting the handwritten signature to a digital form; and receive, from an employer, information identifying the donor, wherein the employer is requesting that a test be performed on the human analyte specimen provided by the donor, and the donor is either an employee or a candidate for employment with the employer;', 'store the information identifying the donor in a donor database;', 'receive, from an employer, information identifying the employer and at least one test requested by the employer to be performed on the specimen;', 'store the information identifying the employer and the at least one test in an employer database;', 'enable a collector associated with a collection facility to access the information identifying the donor from the donor database and the ...

Подробнее
Номер записи: 36
09-03-2017 дата публикации

Interpreting and Supplementing Captured Stroke Information

Номер: US20170068436A1
Автор: Auer Nathaniel E. B., Clark Lee Dicks, Lee Nicole, Markiewicz Jan-Kristian
Принадлежит:

A computer-implemented technique is described herein that receives captured stroke information when a user enters a handwritten note using an input capture device. The technique then performs analysis on the stroke information to produce output analysis information. Based on the output analysis information, the technique then retrieves at least one supplemental information item that is associated with the captured stroke information. The technique then displays the supplemental information item on a canvas display device, together with the original captured stroke information. In effect, the supplemental information item annotates the captured stroke information with meaningful additional information that enhances the value of the captured stroke information. 1. A computer-readable storage medium for storing computer-readable instructions , the computer-readable instructions , when executed by one or more processing devices , performing a method that comprises:receiving captured stroke information from an input capture device, the input capture device producing the captured stroke information in response to capturing freehand ink strokes made by a user on an input surface associated with the input capture device;transforming the captured stroke information into recognized stroke information;automatically performing analysis on the recognized stroke information to generate output analysis information;automatically retrieving at least one supplemental information item based on the output analysis information, without prompting by the user, said at least one supplemental information item being associated with the recognized stroke information; anddisplaying the captured stroke information, together with said at least one supplemental information item, on a canvas display device.2. The computer-readable storage medium of claim 1 , wherein said performing analysis includes determining whether the recognized stroke information specifies one or more entity items.3. The ...

Подробнее
Номер записи: 37
12-03-2015 дата публикации

METHOD OF CONVERTING USER HANDWRITING INTO TEXT INFORMATION AND ELECTRONIC DEVICE FOR PERFORMING THE SAME

Номер: US20150073779A1
Автор: Ahn Hee-Bum, HWANG Seong-Taek, Jung Ho-Young, KIM Do-Hyeon
Принадлежит:

A method, computer-readable storage medium, and device for converting user handwriting into text information by reflecting a paragraph form of the user handwriting in an electronic device is provided. The method includes receiving a handwriting input from a user, recognizing the received handwriting input and converting the recognized handwriting input into text information, recognizing a paragraph form of the received handwriting input, and applying the recognized paragraph form to the converted text information. 1. A method of converting user handwriting into text information by reflecting a paragraph form of the user handwriting in an electronic device , the method comprising:receiving a handwriting input from a user;recognizing the received handwriting input and converting the recognized handwriting input into text information;recognizing a paragraph form of the received handwriting input; andapplying the recognized paragraph form to the converted text information.2. The method of claim 1 , wherein claim 1 ,the paragraph form comprises a paragraph shape, andrecognizing the paragraph form comprises recognizing, as the paragraph shape, at least one selected from indent, outdent, word spacing, alignment, line spacing, and an outline level.3. The method of claim 1 , wherein claim 1 ,the paragraph form comprises a font of a letter included in a paragraph, andrecognizing the paragraph form comprises:calculating an average size of letters included in the handwriting input;recognizing letters, having a size within a predetermined range from the calculated average size, as having a size of a font corresponding to the average size; andrecognizing letters, having a size exceeding a range from the calculated average size, as having a larger font size than the average size.4. The method of claim 1 , wherein claim 1 ,the paragraph form comprises a bullet, andrecognizing the paragraph form comprises recognizing a figure, which distinguishes a sentence or a paragraph, as a ...

Подробнее
Номер записи: 38
27-02-2020 дата публикации

Generating variations of a known shred

Номер: US20200065573A1
Автор: Ehsan Hosseini Asl
Принадлежит: Captricity Inc

Introduced here is a machine learning related technique for supplying an observed model additional training data based upon previously received training data. To determine textual content of a character string based on a digital image that includes a handwritten version of the character string a substantial amount of training data is used. The character string can include one or more characters, and the characters can include any of letters, numerals, punctuation marks, symbols, spaces, etc. Disclosed herein is a technique to determine variations between different images of matching known character strings and substitute those variations into the images in order to create more images with the same known character string.

Подробнее
Номер записи: 39
09-03-2017 дата публикации

Interacting with an Assistant Component Based on Captured Stroke Information

Номер: US20170068854A1
Автор: Auer Nathaniel E. B., Clark Lee Dicks, Lee Nicole, Markiewicz Jan-Kristian, TAKE Katsumi
Принадлежит:

A computer-implemented technique is described herein that receives captured stroke information when a user enters handwritten notes using an input capture device. The technique then automatically performs analysis on the captured stroke information to produce output analysis information. Based on the output analysis information, the technique uses an assistant component to identify a response to the captured stroke information and/or to identify an action to be performed. The technique then presents the response, together with the original captured stroke information. In addition, or alternatively, the technique performs the action. In one case, the response is a text-based response; that text-based response may be presented in a freeform handwriting style to give the user the impression that a virtual assistant is responding to the user's own note. In another case, the response engages the user in an interactive exercise of any type. 1. A computer-readable storage medium for storing computer-readable instructions , the computer-readable instructions , when executed by one or more processing devices , performing a method that comprises:receiving captured stroke information from an input capture device, the input capture device producing the captured stroke information in response to capturing freehand ink strokes made by a user on an input surface associated with the input capture device;transforming the captured stroke information into recognized stroke information;automatically performing analysis on the recognized stroke information to generate output analysis information;identifying, without being prompted to do so by the user, a response to the captured stroke information based on the output analysis information, and/or an action to be performed based on the output analysis information;displaying the captured stroke information on a canvas display device; andpresenting the response to the user and/or performing the action.2. The computer-readable storage medium ...

Подробнее
Номер записи: 40
11-03-2021 дата публикации

Handwritten Diagram Recognition Using Deep Learning Models

Номер: US20210073530A1
Автор: Gerber Andreas, Schaefer Bernhard
Принадлежит:

Systems, methods, and devices are described herein for handwritten diagram recognition using machine learning. A machine learning component receives a digitally encoded image having a handwritten diagram. The machine learning component localizes and classifies a plurality of objects within the handwritten diagram. A structure recognition component identifies connections between each symbol of the plurality of objects based on content of the respective object. A handwriting recognition component interprets one or more alphanumeric text strings within a portion of the plurality of objects. A digital structured model of the digitally encoded image is automatically generated, without human intervention. The digital structured model has the identified connections among the plurality of objects and is in a computer-readable editable format. 1. A method implemented by one or more data processors forming part of at least one computing device , the method comprising:receiving, by a machine learning component, a digitally encoded image comprising a handwritten diagram;localizing and classifying, by the machine learning component, a plurality of objects within the handwritten diagram by defining a plurality of bounding boxes surrounding the plurality of objects based on a feature map extracted from the digitally encoded image, each bounding box surrounding one object, wherein the feature map is a compressed version of the digitally encoded image having pixels of the digitally encoded image mapped to pixels in the compressed version;identifying, by a structure recognition component, connections between each symbol of the plurality of objects based on content of the respective object;interpreting, by a handwriting recognition component, one or more alphanumeric text strings within a portion of the plurality of objects; andautomatically generating, without human intervention, a digital structured model of the digitally encoded image, the digital structured model having the ...

Подробнее
Номер записи: 41
05-06-2014 дата публикации

Color determination device, color determination system, color determination method, information recording medium, and program

Номер: US20140153821A1
Автор: Satoshi Sekine, Soh Masuko
Принадлежит: RAKUTEN INC

In a color determination device ( 101 ) that determines a correspondence relationship between a character string indicating a color and the color indicated by the character string, a character string receiver ( 102 ) receives input of a character string; an image retriever ( 103 ) retrieves for an image relating to the received character string and obtains a plurality of images as a result of the image retrieval; a degree acquirer ( 104 ) represents, with a predetermined accuracy, colors appearing in the plurality of respective images and acquires degrees at which the colors represented with the predetermined accuracy appear in the plurality of images; and a color determiner ( 105 ) determines a color indicated by the received character string from the colors represented with the predetermined accuracy on the basis of the acquired degrees.

Подробнее
Номер записи: 42
16-03-2017 дата публикации

Methods and Systems for Enrollment and Authentication

Номер: US20170076165A1
Автор: Golan Weiss
Принадлежит: Individual

Authentication methods for recognition of a candidate person. During authentication, a previously stored enrollment image is presented on a display to a candidate person. The candidate person is instructed to present a reproduced image of the same scene and/or object to a camera while holding the camera (mobile camera for example) unsupported in free space with respect to the viewed scene or object. Alternatively the candidate person can hold the object unsupported in free space with respect the camera. Using the camera, a candidate image of the viewed scene or object is captured and presented with the previously stored enrollment image. The candidate person aligns the candidate image with the previously stored enrollment image. Upon alignment, the candidate image is verified as an authentic image of the user and the candidate person is authenticated as the user previously enrolled.

Подробнее
Номер записи: 43
21-03-2019 дата публикации

Method and system for csi-based fine-grained gesture recognition

Номер: US20190087654A1
Автор: Hai Jin, JIANG Xiao, Mingxuan NI, Yuxi Wang
Принадлежит: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

The invention provides a method for CSI-based fine-grained gesture recognition, wherein the method comprises the following steps: determining a start point, an end point, a velocity, a direction and/or an inflection point of at least one stroke gesture in multiple dimensions according to an eigenvalue of channel state information; dividing the strokes according to the start point, the end point, the velocity, the direction and/or the inflection point of the stroke using a machine learning method and forming a stroke sequence; building a stroke decipherment model according to frequencies of the strokes appearing in natural language rules and/or scientific language rules and/or connection rules between the strokes; and dividing and recognizing the stroke sequence as a letter sequence, a radical sequence, a numeral sequence and/or a pattern sequence conforming to the natural language rules and/or the scientific language rules using the stroke decipherment model. The present invention involves recognizing strokes of characters from finger gesture, and then recovering characters from the strokes, so as to enrich types of languages that can be recognized from finger gesture and enhance recognition accuracy of gesture writing.

Подробнее
Номер записи: 44
21-03-2019 дата публикации

Handheld Device For Capturing Text From Both A Document Printed On Paper And A Document Displayed On A Dynamic Display Device

Номер: US20190087656A1
Автор: Grover Dale L., King Martin T., Kushler Clifford A., Stafford-Fraser James Q.
Принадлежит:

A device for capturing rendered text is described. The device incorporates one or more visual sensors that receive visual information as a part of capturing rendered text. The visual sensors are collectively capable of capturing both text that is permanently printed on a page, and text that is displayed transitorily on a dynamic device. The device further incorporates a visual information disposition subsystem for disposing of visual information received by the visual sensors. The device further incorporates a package that bears the visual sensors and the visual information disposition subsystem, and is suitable to be held in a human hand. 120-. (canceled)21. A computer-implemented method to capture data from digital images , comprising:receiving, by one or more computing devices, an input to capture digital images;providing, by the one or more computing devices, a user interface that displays instructions to capture digital images;initiating, by the one or more computing devices, an image capturing module of the one or more computing devices;receiving, by one or more computing devices, a digital image from the image capturing module;determining, by the one or more computing devices, that at least a portion of a set of text in the digital image is readable; andin response to determining that at least a portion of the set of text in the digital image is readable, communicating, by the one or more computing devices, the digital image to a processing system.22. The computer implemented method of claim 21 , further comprising:receiving, by the one or more computing devices, an input of an annotation to the digital image; andcommunicating, by the one or more computing devices, the annotation with the digital image to the processing system.23. The computer implemented method of claim 21 , further comprising:determining, by the one or more computing devices, that at least a portion of a set of text in the digital image is not viewable; andproviding, by the one or more ...

Подробнее
Номер записи: 45
19-03-2020 дата публикации

INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM

Номер: US20200089944A1
Автор: SASAGAWA Shigekazu
Принадлежит: FUJI XEROX CO., LTD.

An information processing apparatus includes a receiving unit and a controller. The receiving unit receives an extraction-area image indicating an extraction area. The extraction area includes a fill-in area in which a writer handwrites information. When an instruction to correct a recognition result for the information written in the fill-in area indicated by the extraction-area image is given, the controller causes a display unit to display a different extraction-area image similar to the extraction-area image. 1. An information processing apparatus comprising:a receiving unit that receives an extraction-area image indicating an extraction area, the extraction area including a fill-in area in which a writer handwrites information; anda controller that, when an instruction to correct a recognition result for the information written in the fill-in area indicated by the extraction-area image is given, causes a display unit to display a different extraction-area image similar to the extraction-area image.2. The information processing apparatus according to claim 1 ,wherein the fill-in area is an area formed in a document, andwherein the controller searches, for the different extraction-area image, images indicating a plurality of documents in which the writer has written information, and causes the display unit to display the different extraction-area image.3. The information processing apparatus according to claim 1 ,wherein the controller searches a first image and a second image for the different extraction-area image, and causes the display unit to display the different extraction-area image, the first image indicating a first document in which the fill-in area is formed, the second image indicating a second document of a type identical to a type of the first document.4. The information processing apparatus according to claim 1 ,wherein the controller searches a first image and a second image for the different extraction-area image, and causes the display unit to ...

Подробнее
Номер записи: 46
07-04-2016 дата публикации

ELECTRONIC APPARATUS, PROCESSING METHOD AND STORAGE MEDIUM

Номер: US20160098594A1
Автор: SUGIURA Chikashi
Принадлежит:

According to one embodiment, an electronic apparatus includes a receiver and circuitry. The receiver is configured to receive a first image including a handwritten character. The circuitry is configured to generate first stroke data corresponding to the handwritten character from the first image, acquire a first character code of a character including a stroke indicated by the first stroke data, acquire second stroke data corresponding to the first character code through a search using the first character code, and associate the first image and the second stroke data with each other. 1. An electronic apparatus comprising:a receiver configured to receive a first image comprising a handwritten character; andcircuitry configured to:generate first stroke data corresponding to the handwritten character from the first image;acquire a first character code of a character comprising a stroke indicated by the first stroke data;acquire second stroke data corresponding to the first character code through a search using the first character code; andassociate the first image and the second stroke data with each other.2. The apparatus of claim 1 , wherein the circuitry is configured to acquire the first character code by character recognition processing on the first stroke data.3. The apparatus of claim 1 , wherein the circuitry is configured to compare the first image with a plurality of second images generated from a plurality of second stroke data when the plurality of second stroke data correspond to the first character code claim 1 , and to select one second stroke data from the plurality of second stroke data based on a degree of similarity.4. The apparatus of claim 1 , wherein the circuitry is configured to acquire a plurality of second stroke data corresponding to a plurality of first character codes generated from handwritten characters which are adjacent to each other on the first image through a search using the plurality of first character codes.5. A method of ...

Подробнее
Номер записи: 47
07-04-2016 дата публикации

Partial Overlap and Delayed Stroke Input Recognition

Номер: US20160098595A1
Автор: Deselaers Thomas, Keysers Daniel M., Rowley Henry Allan
Принадлежит:

An optimal recognition for handwritten input based on receiving a touch input from a user may be selected by applying both a delayed stroke recognizer as well as an overlapping recognizer to the handwritten input. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition. 1receiving, by a computing device, a multi-character handwritten input, the multi-character handwritten input comprising a plurality of strokes;applying a delayed stroke recognizer to the multi-character handwritten input to generate a first recognition;generating a delayed stroke recognition score for the first recognition;applying an overlapping recognizer to the multi-character handwritten input to generate a second recognition;generating an overlapping recognition score for the second recognition;comparing the delayed stroke recognition score to the overlapping recognition score; andselecting the first or second recognition based on the comparison as a recognition of the multi-character handwritten input.. A computer-implemented method comprising: This application is a continuation of U.S. application Ser. No. 14/107,007, filed on Feb. 16, 2013, the contents of which are incorporated by reference.In typical handwriting recognition systems, a computer may receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices. Among various recognition techniques, a complete handwriting recognition system also handles formatting, performs correct segmentation into characters and finds the most plausible words. However, such techniques may not perform well when recognizing handwriting input using a user device with limited screen space.According to implementations of the disclosed subject matter, a multi-character handwritten input may be received and may contain a plurality of strokes. A ...

Подробнее
Номер записи: 48
20-04-2017 дата публикации

METHOD FOR IDENTIFYING A CHARACTER IN A DIGITAL IMAGE

Номер: US20170109573A1
Автор: COLLET Frédéric, Dauw Michel, HAUTOT Jordi
Принадлежит:

The invention relates to a method for combining a first Optical Character Recognition (OCR) and a second OCR. The first OCR is run first on an image of string of characters. Its output (first identified characters, positions of the characters and likelihood parameters of the characters) is used to generate a first graph. Segmentation points related to the positions of the first identified characters are used as input by the second OCR performing a combined segmentation and classification on the image of string of characters. The output (second identified characters, positions of the characters and likelihood parameters of the characters) of the second OCR is used to update the first graph to generate a second graph that combines the output of the first OCR with the output of the second OCR. Decision models are then used to modify the weights of paths in the second graph to generate a third graph. A best path is determined on the third graph to obtain the identification of the characters present in the image of string of characters. 1. A method for selecting character candidates in a method for identifying characters in a digital image , the method comprising the steps of:a) applying a first character identification process to determine first character candidates and a list of segmentation points of the first character candidates,b) generating a list of character widths corresponding to a segmentation point from the list of segmentation points,c) determining a portion of the digital image corresponding to the segmentation point and a character width from the list of character widths,d) applying a character classification method on the portion of the digital image to obtain an ID hypothesis of a character possibly present in the portion of the digital image and a likelihood parameter that relates to a likelihood that the ID hypothesis is correct, ande) selecting the ID hypothesis as a second character candidate in the digital image if the likelihood parameter fulfils ...

Подробнее
Номер записи: 49
20-04-2017 дата публикации

System and method for recognition of handwritten diagram connectors

Номер: US20170109579A1
Автор: Claire Sidoli, Fabien Ric, Robin Mélinand, Romain Bednarowicz
Принадлежит: MyScript SAS

A system, method and computer program product for hand-drawing diagrams including text and non-text elements on a computing device are provided. The computing device has a processor and a non-transitory computer readable medium for detecting and recognizing hand-drawing diagram element input under control of the processor. Display of a plurality of input diagram elements in interactive ink is performed on a display device associated with the computing device. At least one diagram element is identified as a connector which connects a plurality of diagram elements. Geometrical characteristics of the at least identified connector are determined and the diagram elements are re-displayed based on one or more interactions received with the interactive ink of the at least identified connector or one or more of the plurality of diagram elements connected thereby and in accordance with the determined geometrical characteristics.

Подробнее
Номер записи: 50
19-04-2018 дата публикации

METHOD AND SYSTEM FOR DIGITIZATION OF DOCUMENT

Номер: US20180109685A1
Автор: Balamurugan Chithralekha, SAMPATH Meera, Stone Leslie, Taylor Rebecca
Принадлежит:

A method and a system for digitization of a document are disclosed. The document is scanned to generate an electronic document. One or more characters in a first set of portions of the electronic document are identified, based on a character recognition technique. Each portion in the first set of portions is classified in one or more groups based on at least a status of identification of the corresponding one or more characters. Further, one or more tasks are created for each of the one or more groups. The one or more tasks are transmitted to one or more crowdworkers, based at least on the respective type of the one or more tasks. Further, a response for each of the one or more tasks is received. Based on the received response, a digitized document is generated. 1. A method for digitization of a document , the method comprising:scanning, by one or more processors, the document to generate an electronic document;identifying, by the one or more processors, one or more characters in a first set of portions of the electronic document based on a character recognition technique;classifying, by the one or more processors, each portion in the first set of portions in one or more groups based on at least a status of identification of the corresponding one or more characters;creating, by the one or more processors, one or more tasks for each of the one or more groups, wherein a type of the one or more tasks created for a group of the one or more groups is different from the type of the one or more tasks created for other group of the one or more groups, wherein each type of the one or more tasks is associated with a cost, wherein the cost of one type of the one or more tasks is different from the cost of other type of the one or more tasks;transmitting, by the one or more processors, the one or more tasks to one or more crowdworkers based at least on the respective type of the one or more tasks;receiving, by the one or more processors, a response for each of the one or more ...

Подробнее
Номер записи: 51
26-04-2018 дата публикации

System and method for managing digital ink typesetting

Номер: US20180114059A1
Автор: Fabien Ric, Robin Mélinand, Romain Bednarowicz
Принадлежит: MyScript SAS

A system, method and computer program product for managing typesetting of digital ink structured content on computing devices. Each computing device has a processor and at least one system application for recognizing handwriting input under control of the processor. The system application determines dimensional information of at least digital ink text elements of structured content, calculates a first font size for each typeset ink text element respectively corresponding to the digital ink text elements based on at least part of the dimensional information, categorizes the typeset ink text elements into one or more categories of the structured content, determines a second font size for each typeset ink text element based on the first font size of each typeset ink text element of the respective category, and display, on a display associated with the computing device, the typeset ink text elements at the respective determined second font sizes.

Подробнее
Номер записи: 52
05-05-2016 дата публикации

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM

Номер: US20160125578A1
Автор: ICHIKAWA Miwa, Koga Yasuyuki, MIZUNUMA Hiroyuki, Ohki Yoshihito, TSUKAHARA Tsubasa, Yamano Ikuo
Принадлежит: SONY CORPORATION

There is provided an image processing apparatus including an input device configured to receive a stroke input, and a display controller configured to control a displaying of a modified stroke, wherein the modified stroke is synthesized based on characteristic parameters of the received stroke input and characteristic parameters of a reference stroke that has been matched to the received stroke input. 1. An image processing apparatus comprising:an input device configured to receive a stroke input; anda display controller configured to control a displaying of a modified stroke,wherein the modified stroke is synthesized based on characteristic parameters of the received stroke input and characteristic parameters of a reference stroke that has been matched to the received stroke input.2. The image processing apparatus of claim 1 , wherein the synthesized modified stroke is an interpolation result generated based on the characteristic parameters of the received stroke input and the characteristic parameters of the reference stroke claim 1 , and the synthesized modified stroke falls between the received stroke input and the reference stroke.4. The image processing apparatus of claim 1 , wherein the modified stroke is provided to the display controller from a server.5. An image processing method comprising:controlling a reception of a stroke input;controlling a determination of characteristic parameters of the received stroke input;controlling a synthesizing of a modified stroke based on the characteristic parameters of the received stroke input and characteristic parameters of a reference stroke that has been matched to the received stroke input; andcontrolling the modified stroke to be displayed.6. The image processing method of claim 5 , wherein the synthesized modified stroke is an interpolation result generated based on the characteristic parameters of the received stroke input and the characteristic parameters of the reference stroke claim 5 , and the synthesized ...

Подробнее
Номер записи: 53
24-07-2014 дата публикации

Sketch Recognition System

Номер: US20140205188A1
Автор: Randall Davis, Tom Yu Ouyang
Принадлежит: Massachusetts Institute of Technology

Handwriting interpretation tools, such as optical character recognition (OCR), have improved over the years such that OCR is a common tool in business for interpreting typed text and sometimes handwritten text. OCR does not apply well to non-text-only diagrams, such as chemical structure diagrams. A method according to an embodiment of the present invention of interpreting a human-drawn sketch includes determining a local metric indicating whether a candidate symbol belongs to a certain classification based on a set of features. The set of features includes, as a feature, scores generated from feature images of the candidate symbol. Also included is determining a joint metric of multiple candidate symbols based on their respective classifications and interpreting the sketch as a function of the local and joint metrics. Sketches can be chemical composition, biological composition, electrical schematic, mechanical, or any other science- or engineering-based diagrams for which human-drawn symbols have well-known counterparts.

Подробнее
Номер записи: 54
04-05-2017 дата публикации

DIGITAL IMAGE PROCESSING APPARATUS AND SYSTEM AND CONTROL METHOD THEREOF

Номер: US20170124389A1
Автор: Kim Jihwan, PARK Sihwa
Принадлежит: LG ELECTRONICS INC.

A head mounted display (HMD) can include a memory, a camera, an image sensor unit configured to sense hand-drawn information via the camera, a display unit configured to display the sensed hand-drawn information or at least one of complete information including the sensed hand-drawn information, the sensed hand-drawn information being partial information, a communication unit, and a controller configured to display the at least one of complete information including the sensed hand-drawn information by accessing the memory or a server. 1. A head mounted display (HMD) , the HMD comprising:a memory;a camera;an image sensor unit configured to sense hand-drawn information via the camera;a display unit configured to display the sensed hand-drawn information or at least one of complete information including the sensed hand-drawn information, the sensed hand-drawn information being partial information;a communication unit; anda controller configured to display the at least one of complete information including the sensed hand-drawn information by accessing the memory or a server.2. The HMD of claim 1 , wherein the controller controls the display unit to display a marker next to the specific complete information if the specific complete information is selected among the at least one of complete information.3. The HMD of claim 2 , wherein the marker has a server transmission attribute claim 2 , further the marker is expressed by at least one of symbols claim 2 , figures claim 2 , characters or numbers.4. The HMD of claim 1 , wherein the controller senses a hand-drawn marker and claim 1 , when the sensed hand-drawn marker is sharing attribute marker claim 1 , further the controller links the sharing attribute marker with the selected complete information and controls the communication unit so as to transmit the selected complete information among along with the sharing attribute marker.5. The HMD of claim 1 , wherein the controller searches for information matching the sensed ...

Подробнее
Номер записи: 55
16-04-2020 дата публикации

Application Launching in a Multi-Display Device

Номер: US20200117473A1
Автор: Chuchro Paula Julia, Disano Robert Joseph, Klein Christian, Nelson Jason Michael, Schenone Scott David, Vasseur Jerome Jean-Louis
Принадлежит:

Techniques for application launching in a multi-display device are described. In one or more implementations, an apparatus such as a mobile device includes multiple interconnected display devices. According to one or more implementations, techniques described herein enable application launching behavior to be determined based on context information. For instance, based on a determined context condition of a multi-display client device, an application launch behavior is determined and used to launch an application on the client device. 1. A computer-implemented method comprising:ascertaining that an application is to be launched on a computing device that is connected with multiple displays;determining a launch behavior for the application based on an evaluation of context information indicating: state information for the multiple displays, and an application state identifying one of a primary launch state for the application and a secondary launch state for the application identified based on the state information for the multiple displays; andlaunching, on the computing device, the application based on the launch behavior.2. The computer-implemented method of claim 1 , wherein the determining of the launch behavior comprises selecting one of the multiple displays to display the application based on analysis of: the state information for the multiple displays and the application state.3. The computer-implemented method of claim 1 , wherein the determining of the launch behavior further comprises selecting one of the primary launch state and the secondary launch state based on analysis of the state information for the multiple displays.4. The computer-implemented method of claim 3 , wherein the selecting selects the primary launch state claim 3 , and wherein the primary launch state identifies that the application is to be launched on one of: an output primary display of the multiple displays or an input primary display of the multiple displays.5. The computer- ...

Подробнее
Номер записи: 56
25-04-2019 дата публикации

OPTICAL CHARACTER RECOGNITION SYSTEMS AND METHODS

Номер: US20190122079A1
Автор: Ackley H. Sprague
Принадлежит:

The present disclosure is generally directed to systems and methods for executing optical character recognition faster than at least some traditional OCR systems, without sacrificing recognition accuracy. Towards this end, various exemplary embodiments involve the use of a bounding box and a grid-based template to identify certain unique aspects of each of various characters and/or numerals. For example, in one embodiment, the grid-based template can be used to recognize a numeral and/or a character based on a difference in centerline height between the numeral and the character when a monospaced font is used. In another exemplary embodiment, the grid-based template can be used to recognize an individual digit among a plurality of digits based on certain parts of the individual digit being uniquely located in specific portions of the grid-based template. 1. A method comprising: applying a grid-based template to a character having a monospaced font;', 'defining in the grid-based template, a first grid section that includes a first portion of the character when the character has a first size and excludes the first portion of the character when the character has a second size that is smaller than the first size; and', 'recognizing the character as a numeral when the first grid section includes the first portion of the character., 'using an optical character recognition system to execute an optical character recognition procedure, the optical character recognition procedure comprising2. The method of claim 1 , whereinthe grid-based template has a rectangular shape,the second size is indicative of a letter of an alphabet, andthe first grid section is selected to provide an indication of a difference in centerline height between the numeral and the letter of the alphabet.3. The method of claim 2 , wherein the first grid section is a portion of a grid pattern that uses numerical coordinates of an x-y mapping system.4. The method of claim 1 , wherein the monospaced font is ...

Подробнее
Номер записи: 57
10-05-2018 дата публикации

System and Method for Performing Screen Capture-Based Sensitive Information Protection Within a Call Center Environment

Номер: US20180129876A1
Автор: Carmiel Yishay, Odinak Gilad
Принадлежит:

Portions of a customer interaction recording that include sensitive information can be identified by performing character recognition on the images in the recording. Field identifiers identified through character recognition are compared to a list of known identifiers of fields for entry of sensitive information. Based on the comparison, field identifiers identified through character recognition can be recognized as sensitive information field identifiers. Images that include the sensitive information field identifiers can be blurred in the stored recording. Further, agent behavior in relation to the screens with fields for entry of sensitive information can be analyzed for purposes such as identifying potentially malicious agent behavior, an agent being in need of assistance, or a recurring customer issue. 1. A system for screen capture-based sensitive information protection within a call center environment , further comprising:at least one video sensor; ["a recording module configured to record via the video sensor a plurality of application screens displayed on a workstation of an agent of a call center during the agent's interaction with a customer, the application screens comprising a plurality of identifiers of fields for entering data items associated with the customer, the recording comprising a plurality of images;", 'a character recognition module configured to perform character recognition to identify the identifiers of the fields within the images;', 'a comparison module configured to compare the identifiers to a list of sensitive information field identifiers;', 'an identification module configured to identify one or more of the recognized identifiers as the sensitive information field identifiers based on the comparison; and', 'a blurring module configured to blur in the recording at least those portions of those images that comprise the data items entered into the fields associated with the sensitive information field identifiers., 'at least one ...

Подробнее
Номер записи: 58
21-05-2015 дата публикации

METHODS AND SYSTEMS FOR RECOGNIZING HANDWRITING IN HANDWRITTEN DOCUMENTS

Номер: US20150139548A1
Автор: Reddy K Sai Praneeth, Srinivasan Akshayaram, Vaya Shailesh
Принадлежит: XEROX CORPORATION

The disclosed embodiments illustrate a method for comparing handwriting in a first electronic document and a second electronic document. The method includes extracting, by one or more processors, one or more segments from a first electronic document and a second electronic document. Each of the one or more segments includes a handwritten text. Thereafter, one or more sets of segments are created from the one or more segments. An information indicating categorization of each segment in a set of segments in one or more categories is received. The information is provided by one or more workers based on the handwriting in each segment. A similarity score based on a count of segments in each of the one or more categories is determined. The similarity score is deterministic of a degree of similarity between the first electronic document and the second electronic document. 1. A method for comparing handwriting , the method comprising:extracting, by one or more processors, one or more segments from a first electronic document and a second electronic document, wherein each of the one or more segments include a handwritten text;creating one or more sets of segments from the one or more segments;receiving, by the one or more processors, an information indicating categorization of each segment in a set of segments in one or more categories, wherein the information is provided by one or more workers based on the handwriting in each segment; anddetermining, by the one or more processors, a similarity score based on a count of segments in each of the one or more categories, wherein the similarity score is deterministic of a degree of similarity between the first electronic document and the second electronic document.2. The method of further comprising modifying claim 1 , by the one or more processors claim 1 , one or more color characteristics associated with each of the first electronic document and the second electronic document.3. The method of further comprising extracting ...

Подробнее
Номер записи: 59
21-05-2015 дата публикации

RETRIEVAL DEVICE AND METHOD AND COMPUTER PROGRAM PRODUCT

Номер: US20150142784A1
Автор: Mihara Isao, SHIBATA Tomoyuki, YAMAJI Yuto
Принадлежит:

According to an embodiment, a retrieval device includes an obtaining controller, a retrieving controller, and a display controller. The obtaining controller obtains handwritten data indicative of a position of a component part of a targeted piece of content. The retrieving controller retrieves, based on the handwritten data, the targeted piece of content from a memory which stores therein one or more pieces of content. The display controller displays a search result on a display. 1. A retrieval device comprising:an obtaining controller configured to obtain handwritten data indicative of a position of a component part of a targeted piece of content;a retrieving controller configured to retrieve, based on the handwritten data, the targeted piece of content from a memory which stores therein one or more pieces of content; anda display controller configured to display a search result on a display.2. The device according to claim 1 , wherein claim 1 , in addition to specifying a position of each of a plurality of component parts of the targeted piece of content claim 1 , the handwritten data further specifies a relative positional relationship among the plurality of component parts.3. The device according to claim 2 , wherein the handwritten data further specifies a type of each of the plurality of component parts.4. The device according to claim 3 , wherein each of the one or more pieces of content is configured to be able to derive a position of each of the plurality of component parts of corresponding one of the one or more pieces of content claim 3 , a relative positional relationship among the plurality of component parts claim 3 , and a type of each of the plurality of component parts.5. The device according to claim 4 , further comprising an assigning controller configured toanalyze each of the one or more pieces of content,generate structural information indicative of the position of each of the plurality of component parts, the relative positional relationship, ...

Подробнее
Номер записи: 60
17-05-2018 дата публикации

SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS

Номер: US20180137349A1
Автор: BROCKLER Frank, HUTKOWSKI Paul, PTUCHA Raymond, Singh Vatsala, SUCH Felipe Petroski
Принадлежит: KODAK ALARIS INC.

Embodiments of the present disclosure include a method for extracting symbols from a digitized object. The method includes processing the word block against a dictionary. The method includes comparing the word block against a word in the dictionary, the comparison providing a confidence factor. The method includes outputting a prediction equal to the word when the confidence factor is greater than a predetermined threshold. The method includes evaluating properties of the word block when the confidence factor is less than the predetermined threshold. The method includes predicting a value of the word block based on the properties of the word block. The method further includes determining an error rate for the predicted value of the word block. The method includes outputting a value for the word block, the output equal to a calculated value corresponding to a value of the word block having the lowest error rate. 1. A system , comprising:at least one processor; and receive a digitized object, the digitized object corresponding to an image including at least one symbol;', 'form digitized line blocks from the digitized object by determining whitespace separators in the digitized object;', 'convert the line blocks into one or more word blocks separated by whitespace, the one or more word blocks having a value associated with the at least one symbol forming the one or more word blocks;', 'resize each word block of the one or more word blocks into a canonical representation of a fixed height;', 'evaluate each word block of the one or more word blocks with a dictionary, the dictionary containing a collection of common words;', 'output a first word prediction when one or more of the word blocks corresponds to a word in the collection;', 'determine a number of symbols and a number of blanks in each word block of the one or more word blocks when the one or more word blocks do not correspond to the collection;', 'evaluate the symbols in the one or more word blocks, the ...

Подробнее
Номер записи: 61
17-05-2018 дата публикации

SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION

Номер: US20180137350A1
Автор: BROCKLER Frank, HUTKOWSKI Paul, PTUCHA Raymond, SUCH Felipe Petroski
Принадлежит: KODAK ALARIS INC.

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block. 1. A system , comprising:at least one processor; and receive a digitized object, the digitized object corresponding to an image including at least one symbol;', 'form digitized line blocks from the digitized object by determining whitespace separators in the digitized object;', 'transform the line blocks into one or more word blocks separated by whitespace, the one or more word blocks having a value associated with at least one symbol forming the one or more word blocks;', 'resize each word block of the one or more word blocks into a canonical representation of a fixed height;', 'evaluate each word block of the one or more word blocks with a dictionary, the dictionary containing a collection of common words;', 'output a first word prediction when one or more of the word blocks corresponds to a word in the collection;', 'assign one or more descriptors to the one or more word blocks when the one more word blocks do not correspond to the collection;', 'perform probabilistic correction on the one or more word blocks; and', 'output a second word prediction, the second word prediction corresponding to the value of the word block., 'memory including instructions that, when executed by the at least ...

Подробнее
Номер записи: 62
28-05-2015 дата публикации

Text input for abugida writing systems with conjuncts

Номер: US20150149952A1
Автор: Abhijeet S. BISAIN, Anirudh Seksaria, Pawan Kumar Baheti, Santanu Chaudhury
Принадлежит: Qualcomm Inc

Disclosed embodiments pertain to a method on a Mobile Station (MS) for input of text for abugida writing systems. In some embodiments, the method may comprise obtaining a base character by performing Optical Character Recognition (OCR) on written user-input on the MS. A conjunct character may also be obtained by applying one or more functional or diacritical operators to the base character. The conjunct character may then be displayed.

Подробнее
Номер записи: 63
26-05-2016 дата публикации

ADAPTIVE GUIDELINES FOR HANDWRITING

Номер: US20160148046A1
Автор: Novak Joshua Neil, Perrin Steven Richard, VanBlon Russell Speight, Zhang Jianbang
Принадлежит:

One embodiment provides a method, involving: receiving, at a device, handwriting input from a user; detecting, using a processor, a location of at least a part of the handwriting input; and providing, on a display device, at least one adaptive line to guide the handwriting input; wherein the at least one adaptive line is positioned based on the location of at least a part of the handwriting input. Other aspects are described and claimed. 1. A method , comprising:receiving, at a device, handwriting input from a user;detecting, using a processor, a location of at least a part of the handwriting input;detecting, using a sensor, an orientation of a display device; andproviding, on the display device, at least one adaptive line to guide the handwriting input based on the location of at least a part of the handwriting input and the orientation of the display device;wherein the position of the at least on adaptive line is independent of currently displayed content.2. The method of claim 1 , wherein positioning of the at least one adaptive line is further determined based on an initial angle of the handwriting input.3. The method of claim 1 , wherein the at least one adaptive line comprises a first line and a second line claim 1 , the first line and the second line being separated by a distance.4. The method of claim 3 , further comprising: positioning the first and second line based on samples of user handwriting.5. The method of claim 4 , wherein the positioning of the first and second line is based upon historical handwriting samples specific to an individual user.6. The method of claim 3 , further comprising positioning the first and second line based on real-time input of user handwriting.7. The method of claim 3 , further comprising:determining an input type for the handwriting input; andpositioning the first and second line based on the input type.8. The method of claim 3 , wherein the distance between the first and second line is based on a third party application ...

Подробнее
Номер записи: 64
30-04-2020 дата публикации

NLP-ASSISTED AUTOMATIC ASSIGNMENT OF DATA PROTECTION POLICIES BASED ON USER INTENTIONS

Номер: US20200134197A1
Автор: Natanzon Assaf, Saad Yossef
Принадлежит:

One example method includes receiving user input concerning a data protection policy for an entity, where the user input is in the form of written input and/or audio input, when the user input comprises audio input, translating the audio input into text, determining an intention of the user with respect to data protection for the entity by translating the text to common terms by interpreting terms of the text that have the same meaning as being similar words and applying context to the words, identifying a data protection policy that best corresponds to the intention of the user concerning data protection for the entity, and applying the data protection policy to the entity. 1. A method , comprising:receiving user input concerning data protection for an entity, wherein the user input is in the form of written input and/or audio input;when the user input comprises audio input, translating the audio input into text; translating the text to common terms by interpreting terms of the text that have the same meaning as being similar words; and', 'applying context to the words;, 'determining an intention of the user with respect to data protection for the entity byidentifying a data protection policy that best corresponds to the intention of the user concerning data protection for the entity; andapplying the data protection policy to the entity so that the entity is protected as provided by the data protection policy.2. The method as recited in claim 1 , wherein application of the data protection policy to the entity is performed automatically.3. The method as recited in claim 1 , wherein when the user input comprises written input claim 1 , the method further comprises translating the written input into text.4. The method as recited in claim 1 , wherein identifying the data protection policy comprises cross-referencing the intention of the user claim 1 , as captured in the user input claim 1 , with one or more of a company policy claim 1 , a repository of regulatory ...

Подробнее
Номер записи: 65
10-06-2021 дата публикации

ELECTRONIC DEVICE AND METHOD FOR PROCESSING WRITING INPUT

Номер: US20210174075A1
Автор: KIM Dohyeon, Kim Jihoon, KIM Jungrim, Kwak Taewon, LEE Donghyuk, LEE Konsang, Lee SeungCheol, LIM Yeunwook, PARK Gibeyong, Park Jeongwan
Принадлежит:

An electronic device and method are disclosed. The electronic device includes a touch-sensitive display, a memory and a processor. The processor implements the method, including: detect a written input including a plurality of strokes through the display, group the plurality of strokes into a first group and a second group based on respective coordinates of each of the plurality of strokes, group first strokes included in the first group into a plurality of blocks, based on a distance between respective coordinates of each of the first strokes, determine a slope for each of the plurality of blocks, rotate an area corresponding to the first group based on the determined slope, execute handwriting recognition on the first strokes based on the rotated area, and displaying a result of the handwriting recognition on the display. 1. An electronic device , comprising:a display;a memory configured to store instructions; andat least one processor electrically connected to the display and the memory,wherein, the stored instructions are executable by the at least one processor to cause the electronic device to:detect a written input including a plurality of strokes through the display;group the plurality of strokes into a first group and a second group based on respective coordinates of each of the plurality of strokes;group first strokes included in the first group into a plurality of blocks, based on a distance between respective coordinates of each of the first strokes;determine a slope for each of the plurality of blocks;rotate an area corresponding to the first group based on the determined slope;execute handwriting recognition on the first strokes based on the rotated area; anddisplay a result of the handwriting recognition on the display.2. The electronic device of claim 1 , wherein the plurality of strokes are grouped into the first group and the second group according to positional similarity between each of the plurality of strokes.3. The electronic device of claim 1 ...

Подробнее
Номер записи: 66
24-05-2018 дата публикации

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM

Номер: US20180144450A1
Автор: ICHIKAWA Miwa, Koga Yasuyuki, MIZUNUMA Hiroyuki, Ohki Yoshihito, TSUKAHARA Tsubasa, Yamano Ikuo
Принадлежит: SONY CORPORATION

There is provided an image processing apparatus including an input device configured to receive a stroke input, and a display controller configured to control a displaying of a modified stroke, wherein the modified stroke is synthesized based on characteristic parameters of the received stroke input and characteristic parameters of a reference stroke that has been matched to the received stroke input. 1. An information processing apparatus , comprising:a display;a touch pad configured to receive a consecutive stroke input given by a user; and recognize the consecutive stroke input including at least two characters, and', 'perform an enlargement processing or a contraction processing on the consecutive stroke input to align the at least two characters based on a bounding box surrounding a character in the consecutive stroke input., 'a processor configured to'}2. The information processing apparatus according to claim 1 , wherein the processor performs the enlargement processing or the contraction processing on the consecutive stroke input to reposition the at least two characters to be aligned according to a new bounding box that is different than the bounding box that surrounded the character in the consecutive stroke input.3. The information processing apparatus according to claim 2 , wherein the new bounding box is located at a different position than the bounding box that surrounded the character in the consecutive stroke input.4. The information processing apparatus according to claim 2 , wherein the new bounding box and the bounding box that surrounded the character in the consecutive stroke input are of different size or shape.5. The information processing apparatus according to claim 1 , wherein the processor performs the enlargement processing or the contraction processing on the consecutive stroke input to reposition the at least two characters to be aligned within new respective bounding boxes that have been resized and aligned.6. The information ...

Подробнее
Номер записи: 67
02-06-2016 дата публикации

SYSTEM AND METHOD FOR RECOGNIZING GEOMETRIC SHAPES

Номер: US20160154998A1
Автор: Buisson Florent, Robin Mélinand
Принадлежит:

A system and method that is able to recognize a user's natural drawing of geometric shapes. The system and method is able to process single-stroke and multi-stroke geometric shapes. It can also apply implicit and user defined constraints to the geometric shapes. The system and method applies these constraints at the vector component level rather than the primitive level. It does this by breaking down both the geometric shapes and constraints on a vector component level. This allows the system and method to handle a larger number of geometric shapes and constraints. After applying the constraints to the geometric shapes at the vector component level, the system and method outputs smooth geometric shapes that incorporated both the implicit and user defined constraints. 1. A computer program product , comprising a computer usable medium having a computer readable program code embodied therein , said computer readable program code adapted to be executed to implement a method for providing geometric shape recognition for at least one input stroke , said method comprising:recognizing at least one primitive that corresponds to at least one input stroke;applying at least one constraint to the at least one primitive, wherein the at least one constraint and at least one primitive are applied on a vector component level; andproviding an output based on the application of the at least one constraint to the at least one primitive.2. The computer program product according to claim 1 , wherein the at least one primitive comprises a plurality of input strokes.3. The computer program product according to claim 1 , wherein the at least one input stroke is at least one user gesture made above an input surface.4. The computer program product according to claim 1 , wherein the at least one input stroke is preprocessed claim 1 , wherein the preprocessing includes at least the normalization and smoothing of the at least one input stroke.5. The computer program product according to claim 4 ...

Подробнее
Номер записи: 68
07-05-2020 дата публикации

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM

Номер: US20200142952A1
Автор: AKITOMO KENJI, Kageyama Hiroyuki
Принадлежит:

The present disclosure provides an information processing apparatus, an information processing method, and a storage medium, capable of improving the display quality after text conversion of a handwritten object, while preserving the layout of the object. The information processing apparatus includes a text converter that character recognizes a handwritten object (A) and converts the handwritten object (A) to text information; an object generator that, when the text conversion processing was performed on a handwritten object (A) that was written by hand right before the handwritten object (A) and a position of the handwritten object (A) is within a predetermined range from a position of the handwritten object (A), determines that a font size corresponding to the handwritten object (A) is the same size as a font size corresponding to the handwritten object (A), and generates a text object (T) corresponding to the handwritten object (A); and a display processor that causes a display to display the text object (T). 1. An information processing apparatus comprising:a text converter that performs text conversion processing to character recognize a first handwritten object written by hand and convert the first handwritten object to text information;a processing determiner that determines whether the text conversion processing was performed on a second handwritten object written by hand right before the first handwritten object;a position determiner that determines whether a position of the first handwritten object is within a predetermined range from a position of the second handwritten object;a size determiner which, when the text conversion processing was performed on the second handwritten object and the position of the first handwritten object is within the predetermined range from the position of the second handwritten object, determines that a font size corresponding to the first handwritten object is the same size as a font size corresponding to the second ...

Подробнее
Номер записи: 69
07-05-2020 дата публикации

DUAL STAGE NEURAL NETWORK PIPELINE SYSTEMS AND METHODS

Номер: US20200143201A1
Автор: Chen Xi, Diallo Mamadou, XUE Qiang
Принадлежит:

A method of identifying and recognizing characters using a dual-stage neural network pipeline, the method including: receiving, by a computing device, image data; providing the image data to a first convolutional layer of a convolutional neural network (CNN); applying, using the CNN, pattern recognition to the image data to identify a region of the image data containing text; providing sub-image data comprising the identified region of the image data to a convolutional recurrent neural network (CRNN); and recognizing, using the CRNN, the characters within the sub-image data. 1. A method of identifying and recognizing characters within a magnetic ink character recognition (MICR) line , the method comprising:receiving an image comprising image data;applying, using a convolutional neural network (CNN), pattern recognition to the image data to produce a CNN resultant matrix, the CNN resultant matrix indicative of an MICR line within the image; and summing up one or more row portions of the CNN resultant matrix to determine a plurality of detection counts, wherein each one of the one or more row portions is associated with a respective detection count; and', 'comparing each of the plurality of detection counts to a predetermined threshold to determine which of the one or more row portions contain data indicative of an MICR line., 'recognizing the MICR line within the CNN resultant matrix by2. The method of claim 1 , wherein the CNN comprises:three fully-connected layers respectively comprise at least 5000 neurons, 2000 neurons, and 1000 neurons, andthe three fully-connected layers respectively comprise less than 10000 neurons, 5000 neurons, and 2000 neurons.3. The method of claim 1 , wherein the predetermined threshold is determined based in part on the number of consecutive rows within the one or more row portions having a nonzero detection count.4. A method of identifying and recognizing one or more specialized character sequences within a document claim 1 , the method ...

Подробнее
Номер записи: 70
22-09-2022 дата публикации

DUPLICATING AND AGGREGATING DIGITAL INK INSTANCES

Номер: US20220300734A1
Автор: COTTLE Aaron D., ESTRADA Julio, SMOLYANSKAYA Irina, Sun Yibo
Принадлежит:

Systems and methods for aggregating digital ink instances within an electronic document. One system includes a memory configured to store instructions and an electronic processor coupled to the memory. The electronic processor, through execution of the instructions in the memory, is configured to receive detected interactions between a touchscreen and a digital pen representing one or more digital strokes within a canvas and determine whether the one or more digital strokes match a predetermined signifier. The electronic processor is also configured to, in response to determining that the one or more digital strokes match the predetermined signifier, determine a first digital ink instance included in the electronic document based on a position of the one or more digital strokes within the canvas, duplicate the first digital ink instance to create a second digital ink instance, and add the second digital ink instance to a designated portion of the electronic document. 1. A system for aggregating digital ink instances within an electronic document , the system comprising:a memory configured to store instructions; and receive detected interactions between a touchscreen and a digital pen representing one or more digital strokes within a canvas;', 'determine whether the one or more digital strokes match a predetermined signifier; and', determine a first digital ink instance included in the electronic document based on a position of the one or more digital strokes within the canvas,', 'duplicate the first digital ink instance to create a second digital ink instance, and', 'add the second digital ink instance to a designated portion of the electronic document., 'in response to determining that the one or more digital strokes match the predetermined signifier], 'an electronic processor coupled to the memory, wherein the electronic processor, through execution of the instructions stored in the memory, is configured to2. The system of claim 1 , wherein the predetermined ...

Подробнее
Номер записи: 71
18-06-2015 дата публикации

Partial Overlap and Delayed Stroke Input Recognition

Номер: US20150169950A1
Автор: Deselaers Thomas, Keysers Daniel Martin, Rowley Henry Allan
Принадлежит: GOOGLE INC.

Systems and techniques are disclosed for selecting an optimal recognition for handwritten based on receiving a touch input from a user and applying both a delayed stroke recognizer as well as an overlapping recognizer to generate the recognition. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition. 1. A computer-implemented method comprising:receiving, by a computing device, a multi-character handwritten input, the multi-character handwritten input comprising a plurality of strokes;applying a delayed stroke recognizer to the multi-character handwritten input to generate a first recognition;generating a delayed stroke recognition score for the first recognition;applying an overlapping recognizer to the multi-character handwritten input to generate a second recognition;generating an overlapping recognition score for the second recognition;comparing the delayed stroke recognition score to the overlapping recognition score; andselecting the first or second recognition based on the comparison as a recognition of the multi-character handwritten input.2. The method of claim 1 , wherein the delayed stroke recognizer and the overlapping recognizer are operated by the computing device.3. The method of claim 1 , wherein at least a portion of the multi-character handwritten input comprising a plurality of strokes is overlapping.4. The method of claim 1 , wherein each character in the multi-character handwritten input is overlapping.5. The method of claim 1 , wherein at least a portion of the multi-character handwritten input is out of horizontal order.6. The method of claim 1 , wherein at least a portion of the multi-character handwritten input is vertically separated.7. The method of claim 1 , wherein the first recognition is based on positional information.8. The method of claim 1 , wherein the positional information is ...

Подробнее
Номер записи: 72
30-05-2019 дата публикации

STROKE BASED SKELETONIZER

Номер: US20190163969A1
Автор: Guarnieri Stuart
Принадлежит: KONICA MINOLTA LABORATORY U.S.A., INC.

A method for processing a stroke in an image is provided. The stroke includes a plurality of pixels and the method includes: executing a modified 4-way stroke width transform (SWT) on a mask of the stroke; determining a plurality of certain centerline points among the pixels based on the modified SWT; generating a plurality of polylines within the stroke based on the certain centerline points; determining a plurality of regions of certainty based on the polylines; removing the regions of certainty from the mask and leaving a plurality of regions of uncertainty in the mask; calculating a plurality of joints and end caps for each of the polylines based on the polylines and the regions of uncertainty; generating a completed polyline path by connecting the polylines based on the joints and end caps; and generating a description of the stroke based on the completed polyline path. 1. A method for processing a stroke in an image , the stroke comprising a plurality of pixels and the method comprising:executing a modified 4-way stroke width transform (SWT) on a mask of the stroke;determining a plurality of certain centerline points among the pixels based on the modified SWT;generating a plurality of polylines within the stroke based on the certain centerline points, wherein each of the polylines is formed of contiguous certain centerline points;determining a plurality of regions of certainty based on the polylines;removing the regions of certainty from the mask and leaving a plurality of regions of uncertainty in the mask;calculating a plurality of joints and end caps for each of the polylines based on the polylines and the regions of uncertainty;generating a completed polyline path by connecting the polylines based on the joints and end caps; andgenerating a description of the stroke based on the completed polyline path.2. The method of claim 1 , wherein executing the modified SWT on the mask of the stroke comprises:generating a stroke width image, a stroke orientation ...

Подробнее
Номер записи: 73
29-09-2022 дата публикации

INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM

Номер: US20220309272A1
Автор: KOSAKA Fumi, MICHIMURA Tadao, OKADA Shigeru, Yoshizuka Masanori
Принадлежит: FUJIFILM Business Innovation Corp.

An information processing apparatus includes a processor configured to acquire each recognition result output by each of plural different recognition processes for the same image, and execute, in relation to the recognition result selected from among the recognition results output by each of the plural recognition processes, a postprocess corresponding to the recognition process from which the selected recognition result is output. 1. An information processing apparatus comprising: acquire each recognition result output by each of a plurality of different recognition processes for the same image; and', 'execute, in relation to the recognition result selected from among the recognition results output by each of the plurality of recognition processes, a postprocess corresponding to the recognition process from which the selected recognition result is output., 'a processor configured to2. The information processing apparatus according to claim 1 , wherein the processor is configured to:acquire a certainty degree which each of the plurality of recognition processes outputs in association with the recognition result, andexecute the postprocess on the selected recognition result based on the certainty degree.3. The information processing apparatus according to claim 1 , wherein the processor is configured to:execute, in a case where the recognition process from which the selected recognition result is output is a handwritten text recognition process, a confidentiality process for the selected recognition result or the image, as the postprocess.4. The information processing apparatus according to claim 2 , wherein the processor is configured to:execute, in a case where the recognition process from which the selected recognition result is output is a handwritten text recognition process, a confidentiality process for the selected recognition result or the image, as the postprocess.5. The information processing apparatus according to claim 1 ,wherein the image is an image of ...

Подробнее
Номер записи: 74
25-06-2015 дата публикации

OCR ENABLED MANAGEMENT OF ACCOUNTS PAYABLE AND/OR ACCOUNTS RECEIVABLE AUDITING DATA

Номер: US20150178855A1
Автор: FLYNN Joseph, JRAIGE Wassim G., KOITZSCH Kerry Edward
Принадлежит:

A number of different tags are input in a fax cover sheet that tell an OCR system not only the identity of the supplier, but also to which client the document should be routed. The OCR system identifies a number of these tags and compares them to stored supplier data to validate to which supplier the document belongs. If the system cannot validate the document, it is routed to a GUI for manual sorting. If there is no coversheet, the system relies upon the OCR system to locate keywords on the document and caller ID information to suggest a correct supplier. The OCR system also clips a separate, horizontal slice of the document (‘snippet’) that corresponds to the display of any line item and places it in a data base for future reference and reporting. The application collects and associates all corresponding snippets to their originating line items. 1. A method comprising:receiving a document comprising a plurality of tags;identifying at least some of the plurality of tags;comparing the identified tags to supplier data stored in a database to validate the document;clipping a portion of the document that corresponds to a line item;storing the clipped portion and the originating line item in the database;associating the clipped portion with the originating line item;tagging a location of the originating line item to its original location in the document; andcausing the originating line item to be presented on a graphical user interface, the originating line item comprising a first link to the document and a second link to the corresponding clipped portion.2. The method of claim 1 , further comprising:determining whether any tables are in the document; andresponsive to determining a table is present, identifying any column headers in the table and comparing the column headers to headers in a table master.3. The method of claim 2 , further comprising:scanning through an entirety of the document;marking the originating line item on a digital representation of the document, ...

Подробнее
Номер записи: 75
23-06-2016 дата публикации

CANDIDATE HANDWRITING WORDS USING OPTICAL CHARACTER RECOGNITION AND SPELL CHECK

Номер: US20160179941A1
Автор: Novak Joshua Neil, Perrin Steven Richard, VanBlon Russell Speight, Zhang Jianbang
Принадлежит:

One embodiment provides a method, including: receiving, in an overlay handwriting application, one or more handwriting strokes; processing the one or more handwriting strokes to obtain at least one candidate machine input word; generating, using a spell check application, at least one spell check word using the at least one candidate machine input word; and providing, on a display device, the at least one spell check word generated by the spell check application. Other embodiments are described and claimed. 1. A method , comprising:receiving, in an overlay handwriting application, one or more handwriting strokes;processing the one or more handwriting strokes to obtain at least one candidate machine input word;generating, using a spell check application, at least one spell check word using the at least one candidate machine input word; andproviding, on a display device, the at least one spell check word generated by the spell check application.2. The method of claim 1 , further comprising:selecting, from the at least one candidate machine input word, a machine input word;wherein the generating comprises, generating a list comprising at least one spell check word; andwherein the providing comprises, providing the generated list.3. The method of claim 2 , further comprising filtering the list comprising at least one spell check word generated by the spell check application prior to the providing.4. The method of claim 3 , wherein the filtering comprises selecting words included in two or more lists comprising at least one spell check word.5. The method of claim 3 , wherein the filtering comprises weighting the list comprising at least one spell check word according to a spell check confidence score.6. The method of claim 3 , wherein the filtering comprises weighting the list comprising at least one spell check word according to a candidate machine input score.7. The method of claim 2 , further comprising ranking the list comprising at least one spell check word ...

Подробнее
Номер записи: 76
21-06-2018 дата публикации

MANAGING REAL-TIME HANDWRITING RECOGNITION

Номер: US20180173415A1
Автор: Bellegarda Jerome R., DIXON Ryan S., DOLFING Jannes G., GROETHE Karl M., MEIER Ueli, Misra Karan, XIA Mei-Qun
Принадлежит:

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed. 1. A method , comprising: receiving, via the touch-sensitive surface, a handwriting input from a user, the handwriting input comprising a plurality of handwritten strokes provided in a handwriting input area of a handwriting input interface;', 'recognizing, based on a handwriting recognition model, a plurality of output characters from the handwriting input, the plurality of output characters including at least a first emoji character and at least a first character from a script of a natural human language; and', 'displaying, on the display, a recognition result comprising the first emoji character and the first character from the script of the natural human language in a candidate display area of the handwriting input interface., 'at a device with a display and a touch-sensitive surface2. The method of claim 1 , further comprising:based on the handwriting recognition model, recognizing at least a first semantic unit from the handwriting input, wherein the first semantic unit comprises a respective character, word or phrase that is capable of conveying a respective semantic meaning in a respective human language;identifying a second emoji character associated with the first semantic unit recognized from the ...

Подробнее
Номер записи: 77
22-06-2017 дата публикации

WRITING BOARD DETECTION AND CORRECTION

Номер: US20170177931A1
Автор: Fang Gang
Принадлежит:

A method for image processing, including: obtaining an image including a writing board and a background external to the writing board; detecting a plurality of lines within the image; determining, based on the plurality of lines, a plurality of corners of the writing board within the image; and correcting a perspective of the writing board by applying a transformation to the image based on the plurality of corners. 1. A method for image processing , comprising:obtaining an image comprising a writing board and a background external to the writing board;detecting a plurality of lines within the image;identifying and removing, from the plurality of lines, a first subset of lines located on the writing board in the image;identifying and removing, from the plurality of lines, a second subset of lines located in the background of the image;determining, based on the plurality of lines after the first subset and the second subset are removed, a plurality of corners of the writing board within the image; andcorrecting a perspective of the writing board by applying a transformation to the image based on the plurality of corners.2. The method of claim 1 , wherein identifying and removing the first subset of lines comprises:selecting a line of the plurality of lines;identifying a first plurality of intensity values for a first plurality of pixels on a first side of the line;identifying a second plurality of intensity values for a second plurality of pixels on a second side of the line;determining the line is located on the writing board based on the first plurality of pixel values and the second plurality of pixel values; andremoving, before determining the plurality of corners, the line from the plurality of lines in response to determining the line is located on the writing board.3. The method of claim 2 , wherein identifying and removing the first subset of lines further comprises:generating a plurality of strips crossing the line from the first side of the line to the ...

Подробнее
Номер записи: 78
28-05-2020 дата публикации

INPUT DISPLAY DEVICE AND INPUT DISPLAY METHOD

Номер: US20200167014A1
Автор: KOYAMA Noriyuki, TERADA Satoshi
Принадлежит:

An input display device includes a display unit that displays a screen for handwriting input on an input screen including a plurality of input fields, a stroke data processing unit that groups stroke data which is input to a capture screen by handwriting into stroke data representing characters to generate grouped stroke data as grouping stroke data, a character recognition unit that conducts character recognition on the grouping stroke data to convert the grouping stroke data into at least one recognized character, and a control processing unit that displays the at least one recognized character at the plurality of input fields of the input screen correlated with positions, at which handwriting input was performed, in the screen for handwriting input. 1. An input display device comprising:a display that displays a input screen including an input field for handwriting input;a stroke data generator that generates grouping stroke data by grouping stroke data which is included in handwriting input to the input screen;a character recognition processor that conducts character recognition on the grouping stroke data to convert the grouping stroke data into a recognized character; andan image processor that displays the recognized character on the display screen, whereinwhen there is a handwriting input by a user in the input field,the character recognition processor conducts character recognition on the grouping stroke data generated from the handwriting input by the stroke data generator, andthe image processor displays the recognized character on the input field on the basis of the input field and attribute information of the input field.2. The input display device according to claim 1 , whereinthe attribute information is at least information for selection or designation by a user of the input field.3. The input display device according to claim 1 , whereinwhen the attribute information is information for selection of the input field corresponding to the attribute ...

Подробнее
Номер записи: 79
30-06-2016 дата публикации

COMPUTER-READABLE RECORDING MEDIUM, METHOD, AND APPARATUS FOR CHARACTER RECOGNITION

Номер: US20160188970A1
Автор: Kataoka Masahiro, MATSUDA Yugo, TSUYUKI Yasuhiro
Принадлежит: FUJITSU LIMITED

A character recognition apparatus includes a storage and a processor that executes a method including generating input stroke data from input coordinate data corresponding to an input operation, generating stroke combination candidates and evaluation data corresponding to the stroke combination candidates from the input stroke data, the stroke candidates including target verification strokes combined to constitute target verification characters, identifying a first stroke combination from the stroke combination candidates based on appearance probability of the target verification strokes, appearance probability data of each stroke stored in the storage, and the evaluation data, and outputting a character corresponding to the input operation based on the first stroke combination. The appearance probability indicates a probability in which the target verification strokes appear in each of the target verification characters. The appearance probability data is generated based on the appearance probability of the target verification strokes. 1. A non-transitory computer-readable recording medium storing therein a character recognition program that causes a computer to execute a process comprising:generating input stroke data from input coordinate data corresponding to an input operation,generating a plurality of stroke combination candidates and evaluation data corresponding to the plurality of stroke combination candidates from the input stroke data, the plurality of stroke candidates including target verification strokes that are combined to constitute one or more target verification characters,identifying a first stroke combination from the plurality of stroke combination candidates based on appearance probability of the target verification strokes, appearance probability data of each stroke stored in a storage device, and the evaluation data, andoutputting a character corresponding to the input operation based on the first stroke combination;wherein the appearance ...

Подробнее
Номер записи: 80
29-06-2017 дата публикации

Graphical handwriting sign-in method and system

Номер: US20170185722A1
Автор: Dung Tien Vu, Hieu Ngoc Vu, Khue Ngoc Vu, Thu Minh Vu, Truong Mien Vu
Принадлежит: Individual

A computer network system and method of receiving, storing, and authenticating a user's presence and information obtained at geographical user-location is disclosed. A first device displays a plurality of input regions on its display screen. Utilizing a stylus or fingertip, the user enters hand-written inputs in those regions. The first device transmits the user hand-written inputs and geographical location to a server and subsequently removes the displayed plurality of hand-written inputs from the plurality of input regions for the next user. A server receives the user's hand-written inputs and location, associates the location to the user, stores them, and transmits them to a second device where, in real time, they are displayed on a display screen of the second device, facilitating authentication and verification of the user's presence and user's hand-written inputs. In addition, authenticating documents comprising the hand-written inputs may be generated for audits.

Подробнее
Номер записи: 81
04-06-2020 дата публикации

MANAGING REAL-TIME HANDWRITING RECOGNITION

Номер: US20200174658A1
Автор: Bellegarda Jerome R., DIXON Ryan S., DOLFING Jannes G., GROETHE Karl M., MEIER Ueli, Misra Karan, XIA Mei-Qun
Принадлежит:

Methods, systems, and computer-readable media related to a technique for providing handwriting input functionality on a user device. A handwriting recognition module is trained to have a repertoire comprising multiple non-overlapping scripts and capable of recognizing tens of thousands of characters using a single handwriting recognition model. The handwriting input module provides real-time, stroke-order and stroke-direction independent handwriting recognition for multi-character handwriting input. In particular, real-time, stroke-order and stroke-direction independent handwriting recognition is provided for multi-character, or sentence level Chinese handwriting recognition. User interfaces for providing the handwriting input functionality are also disclosed. 1. A electronic device , comprising:a display;a touch-sensitive surface;one or more processors; andmemory storing one or more programs configured to be executed by the one or more processors, receiving a handwriting input, the handwriting input comprising a plurality of handwritten strokes provided in an handwriting input area of a handwriting input interface;', 'identifying a plurality of recognition units from the plurality of handwritten strokes, each recognition unit including a respective subset of the plurality of handwriting strokes;', 'generating a multi-character recognition result comprising respective characters recognized from the plurality of recognition units;', 'displaying the multi-character recognition result in a candidate display area of the handwriting input interface;', 'while the multi-character recognition result is displayed in the candidate display area, receiving a deletion input; and', 'in response to receiving the deletion input, removing an end character from the multi-character recognition result displayed in the candidate display area., 'the one or more programs including instructions for2. The electronic device of claim 1 , wherein the one or more programs further including ...

Подробнее
Номер записи: 82
05-07-2018 дата публикации

MACHINE PRINT, HAND PRINT, AND SIGNATURE DISCRIMINATION

Номер: US20180189558A1
Автор: Amtrup Jan W., Macciola Anthony, Shustorovich Alexander, Thrasher Christopher W.
Принадлежит:

Computer program products for discriminating hand and machine print from each other, and from signatures, are disclosed and include program code readable and/or executable by a processor to: receive an image, determine a color depth of the image; reducing the color depth of non-bi-tonal images to generate a bi-tonal representation of the image; identify a set of one or more graphical line candidates in either the bi-tonal image or the bi-tonal representation, the graphical line candidates including true graphical lines and/or false positives; discriminate any of the true graphical lines from any of the false positives; remove the true graphical lines from the bi-tonal image or the bi-tonal representation without removing the false positives to generate a component map comprising connected components and excluding graphical lines; identify one or more of the connected components in the component map; and output and/or display and indicator of each of the connected components. 1. A computer program product comprising: a non-transitory computer readable storage medium having program code embodied therewith , the program code readable and/or executable by a processor to:receive an image;determine a color depth of the received image, the color depth corresponding to at least one of grayscale, bi-tonal and color;reduce the color depth of the received image to generate a bi-tonal representation of the image in response to determining the color depth of the received image is not bi-tonal;identify a set of one or more graphical line candidates in the bi-tonal representation, the graphical line candidates including one or more of true graphical lines and false positives;discriminate any of the true graphical lines from any of the false positives;remove the true graphical lines from the bi-tonal representation without removing the false positives to generate a component map comprising connected components and excluding graphical lines;identify one or more of the connected ...

Подробнее
Номер записи: 83
22-07-2021 дата публикации

INFORMATION PROCESSING APPARATUS THAT CREATES PROCESSED TEXT DATA FROM TEXT DATA, BY CHANGING ORDER OF SENTENCES IN TEXT DATA, AND IMAGE FORMING APPARATUS

Номер: US20210227081A1
Автор: ARRIOLA Dennis, ORBANEJA Rowel
Принадлежит: KYOCERA Document Solutions Inc.

An information processing apparatus includes an image reading device, and a control device that acts as a text converter, a divider, an extractor, and a text processor. The text converter converts a source image acquired by the image reading device from the source document, into text data. The divider divides the text data converted by the text converter into a plurality of text groups, using a predetermined criterion. The extractor extracts, from the plurality of text groups divided by the divider, a key text group containing a specific word identified by a predetermined rule, among words contained in the text data constituting the plurality of text groups. The text processor creates processed text data by placing the key text group at a head position, and placing remaining text groups other than the key text group in the plurality of text groups, at a position subsequent to the key text group. 1. An information processing apparatus comprising:an image reading device that reads an image of a source document; and a text converter that converts a source image acquired by the image reading device through reading of the source document, into text data;', 'a divider that divides the text data converted by the text converter into a plurality of text groups, using a predetermined criterion;', 'an extractor that extracts, from the plurality of text groups divided by the divider, a key text group containing a specific word identified by a predetermined rule, among words contained in the text data constituting the plurality of text groups; and', 'a text processor that creates processed text data by placing the key text group at a head position, and placing remaining text groups other than the key text group in the plurality of text groups, at a position subsequent to the key text group., 'a control device including a processor, and configured to act, when the processor executes a control program, as2. The information processing apparatus according to claim 1 ,wherein the ...

Подробнее
Номер записи: 84
30-07-2015 дата публикации

NOTE RECOGNITION AND ASSOCIATION BASED ON GROUPING INDICATORS

Номер: US20150213310A1
Автор: Åkerlund Linus, Axelsson Pontus, Bastiaens Willem V., Mahli David M., Moore Richard J., Moran Cristin E., Nakayama Tasuku, Persson Roland, Rotstein Michael, Somasundaram Guruprasad, Wolk Diane R.
Принадлежит:

Techniques are described for creating and manipulating software notes representative of physical notes. A computing device is described that includes a processor and an image collection module executable on the processor and configured to receive an input image of an environment having a plurality of physical notes. An image processing engine executable on the processor is configured to identify the plurality of physical notes in the input image and generate, for each of the physical notes, a corresponding digital note. The image processing engine is further configured to identify an indication of one or more groups of the plurality of identified notes in the input image and group the plurality of digital notes according to the indication. 1. A method comprising:receiving, by a computing device, an input image of an environment having a plurality of physical notes;processing the input image with the computing device to identify the plurality of physical notes in the input image;generating, by the computing device, a plurality of digital notes corresponding to the plurality of notes identified in the input image, wherein the plurality of digital notes include information represented by the plurality of notes in the input image;identifying, by the computing device, an indication of one or more groups of the plurality of physical notes based on an user input; andgrouping, by the computing device, the plurality of digital notes according to the indication of the one or more groups.2. The method of claim 1 , wherein the user input comprises a gesture.3. The method of claim 2 , wherein the user input comprises a gesture on a presence-sensitive display of device.4. The method of claim 2 , wherein the user input comprises a gesture indicating selections of one or more of the plurality of the physical notes.5. The method of claim 1 , further comprising:displaying, by the computing device, the one or more groups of the plurality of digital notes.6. A method claim 1 , ...

Подробнее
Номер записи: 85
20-07-2017 дата публикации

SYSTEM AND METHOD FOR RECOGNIZING MULTIPLE OBJECT STRUCTURE

Номер: US20170206406A1
Автор: ONIS Sebastien
Принадлежит:

A system, method, and computer program for recognizing an arrangement of multiple objects on computing devices. The computing device may include a processor and at least one non-transitory computer readable medium for recognizing handwriting input under control of the processor. The non-transitory computer readable medium may be configured to determine with the medium at least one geometrical relationship between a plurality of recognized elements of the input and allocate with the medium the recognized elements having the at least one geometrical relationship therebetween to corresponding positions of an arrangement of the recognized elements. The positions of the arrangement may be cells of a two-dimensional structure of the recognized elements. The at least one geometrical relationship may be an overlap of the plurality of recognized elements in one or more directions of the arrangement. 1. A system for recognizing an arrangement of multiple objects on computing devices , each computing device comprising a processor , a memory and at least one non-transitory computer readable medium for recognizing handwriting input under control of the processor , the at least one non-transitory computer readable medium configured to:determine, with the medium, at least one geometrical relationship between a plurality of recognized elements of the input; andallocate, with the medium, the recognized elements having the at least one geometrical relationship therebetween to corresponding positions of an arrangement of the recognized elements.2. A system as claimed in claim 1 , wherein the positions of the arrangement are cells of a two-dimensional structure of the recognized elements3. A system as claimed in claim 1 , wherein the at least one geometrical relationship is an overlap of the plurality of recognized elements in one or more directions of the arrangement.4. A system as claimed in claim 3 , the at least one non-transitory computer readable medium configured to determine ...

Подробнее
Номер записи: 86
20-07-2017 дата публикации

MODEL-DRIVEN EVALUATOR BIAS DETECTION

Номер: US20170206504A1
Автор: Larsen Loren, Taylor Benjamin
Принадлежит:

A method for detecting bias in an evaluation process is provided. The method includes operations of receiving evaluation data from a candidate evaluation system. The evaluation data is provided by a set of evaluators based on digital interview data collected from evaluation candidates. The operations of the method further include extracting indicators of characteristics of the evaluation candidates from the digital interview data, classifying the evaluation candidates based on the indicators extracted from the digital interview data, and determining whether the evaluation data indicates a bias of one or more evaluators with respect to a classification of the evaluation candidates. 1. A method comprising:retrieving, by a human bias detection tool executed by a computing device of a digital interviewing platform, evaluation data from a data storage device, the evaluation data generated with respect to a set of evaluators who evaluated recorded video responses of first candidates to questions asked during a hiring process;performing, by the human bias detection tool, video analysis on video frames of the video responses to identify visual indicators of faces of the first candidates, wherein the visual indicators comprise one or more facial features;combining, by the human bias detection tool, the visual indicators with an audio indicator that further characterizes respective first candidates, to generate a combined vector representation of the first candidates;performing, by the human bias detection tool, supervised learning of the combined vector representation of the first candidates with respect to one or more classifications of the first candidates, to train a classification model;applying, by the human bias detection tool, the classification model to second indicators captured of second candidates to classify the second candidates according to a protected class, wherein the second indicators comprise one or more of a second visual indicator or a second audio ...

Подробнее
Номер записи: 87
04-07-2019 дата публикации

METHOD AND APPARATUS FOR EVALUATING A USER-SPECIFIED PATH IN AN ACTIVITY

Номер: US20190205777A1
Автор: Gillies Murray Fulton, KLAMING Laura, VAN MINDE Daisy, VLASKAMP Björn Nicolaas Servatius
Принадлежит: KONINKLIJKE PHILIPS N.V.

There is provided a method for evaluating a user-specified path in an activity in which the user is to select a plurality of targets, the method in an electronic device comprising receiving information on a plurality of targets and information on the user-specified path; defining a respective evaluation area for each target; and determining whether the user has successfully selected a first target in the plurality of targets by: determining from the user-specified path an entry point for the user-specified path into the evaluation area for the first target and an exit point for the user-specified path out of the evaluation area for the first target; determining a first measure of similarity being a measure of similarity for the part of the user-specified path in the evaluation area for the first target and a first path that is a straight line from the determined entry point to the determined exit point; determining a second measure of similarity being a measure of similarity for the part of the user-specified path in the evaluation area for the first target and a second path formed from a first straight-line section from the determined entry point to the first target and a second straight-line section from the first target to the determined exit point; and comparing the determined first and second measures of similarity to determine whether the user has successfully selected the first target. 1. A method for evaluating a user-specified path in an activity in which the user is to select a plurality of targets , the method in an electronic device comprising:receiving information on a plurality of targets and information on the user-specified path;defining a respective evaluation area for each target; and determining from the user-specified path an entry point for the user-specified path into the evaluation area for the first target and an exit point for the user-specified path out of the evaluation area for the first target;', 'determining a first measure of ...

Подробнее
Номер записи: 88
04-08-2016 дата публикации

METHOD, APPARATUS AND MOBILE TERMINAL FOR SPEED DIAL WITHIN PAGE

Номер: US20160227015A1
Автор: Fan Di
Принадлежит:

A method for speed dial is disclosed. The method includes generating a transparent or semitransparent mask layer on a region of a currently displayed page according to a designated trigger instruction; obtaining input information of a user on the mask layer; determining dial information according to the input information; and dialing a number according to the dial information. The present disclosure further provides a dial apparatus and a mobile terminal for speed dial correspondingly. The present disclosure is able to implement speed dial without exiting a page that is currently browsed, thus being more convenient in use and improving user experience. 1. A method comprising:generating a mask layer on a region of a page that is currently displayed in a screen of a mobile terminal according to a designated trigger instruction;obtaining input information from a user on the mask layer;determining dial information based at least in part on the input information; andperforming a dialing based at least in part on the dial information.2. The method of claim 1 , wherein the mask layer includes a div layer claim 1 , and the div layer covers at least a portion of the region of the page that is currently displayed.3. The method of claim 1 , wherein performing the dialing comprises:invoking a dialing program interface; andsending the dial information to the dialing program interface for performing the dialing.4. The method of claim 1 , wherein generating the mask layer comprises setting at least a portion of the region of the page to be visible.5. The method of claim 1 , wherein the designated trigger instruction comprises a set function key of the mobile terminal being pressed for a set time length.6. The method of claim 1 , wherein obtaining the input information comprises receiving handwriting input content on the mask layer claim 1 , and wherein determining the dial information comprises invoking a handwriting recognition program to recognize the handwriting input content ...

Подробнее
Номер записи: 89
11-07-2019 дата публикации

BIOMETRIC AUTHENTICATION OF ELECTRONIC SIGNATURES

Номер: US20190213430A1
Автор: Schwartz Steven R.
Принадлежит:

At least one contemporaneous signature image is captured while a user generates an electronic signature for a document. When one or more contemporaneous signature images maps to a verification image, signature data representative of an electronic signature is associated with the document. 1. A device comprising:a camera configured to initiate image captures of received imaging light;a display disposed to emit display light; and render, with the display, a document;', 'receive, via the input interface, a signature input representing a user initiating an electronic signature with the input interface;', 'in response to receiving the signature input with the input interface, capturing a contemporaneous signature image with the camera to capture the user inputting a remainder of the electronic signature, the contemporaneous signature image includes at least a portion of an eye of the user;', 'storing signature data representing the electronic signature received by the input interface;', 'comparing the contemporaneous signature image to a verification image; and', 'associating the signature data to the document when the contemporaneous signature image maps to the verification image., 'an input interface, wherein the device is configured to2. The device of claim 1 , wherein the device further comprises a communication module coupled to send and receive data claim 1 , and wherein comparing the contemporaneous signature image to the verification image includes:transmitting, with the communication module, a verification request from the device to a computing device, wherein the verification request includes user credentials of the user of the device; andreceiving, with the communication module, the verification image from the computing device.3. The device of further comprising a memory claim 1 , wherein the verification image is stored in the memory claim 1 , and wherein comparing the contemporaneous signature image to the verification image includes accessing the ...

Подробнее
Номер записи: 90
18-07-2019 дата публикации

METHOD OF PROCESSING AND RECOGNIZING HAND-WRITTEN CHARACTERS

Номер: US20190220684A1
Автор: Provencher Samuel David
Принадлежит: Boston Inventions, LLC

The present disclosure relates to a method and system of processing original handwriting input, the system and method being capable of recognize a plurality of strokes provided on the input recognition interface, the method including: determining a stroke box around each stroke; determining overlap between the stroke boxes; correlating overlapping stroke boxes to one or more characters; providing a character box around each of the one or more characters; determining overlap between character boxes; correlating overlapping character boxes to one or more words; providing a word box around each of the one or more words; provide a word margin around each of the one or more word boxes; determining overlap between each word box to determine a line; wherein each of the characters, words, or lines can be individually selected and rearranged, the system automatically adjusting spacing or placement of surrounding elements to allow for the rearrangement. 1. A handwriting recognition and processing system , the system comprising:a non-transitory computer-readable medium;an input recognition interface; and recognize a plurality of strokes provided on the input recognition interface;', 'determine a stroke box around each stroke;', 'provide a stroke margin around each of the stroke boxes;', 'determine overlap between the stroke margins for each stroke box;', 'correlate overlapping stroke margins to one or more characters;', 'provide a character box around each of the one or more characters; and', 'provide a character margin around each of the one or more character boxes., 'processing circuitry operably connected to the non-transitory computer-readable medium and the input recognition interface, the processing circuitry being configured to perform the following tasks2. The handwriting recognition and processing system of claim 1 , wherein the processing circuitry is further configured to perform the following tasks:determine overlap between the character margins for each character ...

Подробнее
Номер записи: 91
17-08-2017 дата публикации

ELECTRONIC APPARATUS, METHOD, AND PROGRAM

Номер: US20170236004A1
Автор: SUGIURA Chikashi
Принадлежит:

According to one embodiment, an electronic apparatus performs a character recognition process, uses, if a stroke in a first area of the first handwritten document and a stroke in a second area are the same, a character recognition result of the first handwritten document, and performs, if a stroke in the first area and a stroke in the second area are different, the character recognition process for the second area including the different stroke. 1. An electronic apparatus for performing a character recognition process for strokes in a handwritten document , the electronic apparatus configured to:compare a first handwritten document and a second handwritten document, wherein the first handwritten document comprises first areas, each of the first areas comprises strokes, the character recognition process for the first handwritten document is performed at a first time, the second handwritten document is created by editing the first handwritten document and comprises second areas, each of the second areas comprises strokes, and the character recognition process for the second handwritten document is performed at a second time later than the first time;use, when a stroke in at least one of the first areas and a stroke in at least one of the second areas are same, at least a part of a character recognition result of the at least one of the first areas of the first handwritten document when performing the character recognition process of the second area excluding the at least one of the second areas comprising the same stroke; andperform, when a stroke in at least one of the first areas and a stroke in at least one of the second areas are different, the character recognition process for the second area including the different stroke.2. The electronic apparatus of claim 1 , further comprising a memory configured to store a created handwritten document wherein a handwritten document read from the memory is overwritten in the memory claim 1 ,wherein the first handwritten ...

Подробнее
Номер записи: 92
25-08-2016 дата публикации

Methods and systems for efficient automated symbol recognition using decision forests

Номер: US20160247019A1
Автор: Oleg Senkevich, Yury Georgievich Chulinin
Принадлежит: ABBYY Development LLC

The current document is directed to methods and systems for identifying symbols corresponding to symbol images in a scanned-document image or other text-containing image, with the symbols corresponding to Chinese or Japanese characters, to Korean morpho-syllabic blocks, or to symbols of other languages that use a large number of symbols for writing and printing. In one implementation, the methods and systems to which the current document is directed carry out an initial processing step on one or more scanned images to identify a set of graphemes that most likely correspond to each symbol image that occurs in the scanned document image. The graphemes are selected for a symbol image based on accumulated votes generated from symbol patterns identified as likely related to the symbol image using one or more decision forests.

Подробнее
Номер записи: 93
25-08-2016 дата публикации

HEAD MOUNTED DISPLAY, INFORMATION PROCESSING SYSTEM AND INFORMATION PROCESSING METHOD

Номер: US20160247323A1
Автор: SHIMAZAKI Takeshi
Принадлежит: RICOH COMPANY, LTD.

A transmissive head mounted display includes an imaging device to acquire an image of a real space, the real space including at least a medium to which a user can physically add handwriting; a display to display a virtual image of electronic data to the user so as to be superimposed on the medium in the real space using the acquired image of the real space; and processing circuitry configured to acquire an image of the real space including at least the medium having the handwringing of the user added, extract handwritten information from the image of the real space including at least the medium having the handwriting of the user added, and superimpose the extracted handwritten information on an image of the electronic data. 1. A transmissive head mounted display , comprising:an imaging device to acquire an image of a real space, the real space including at least a medium to which a user can physically add handwriting;a display to display a virtual image of electronic data to the user so as to be superimposed on the medium in the real space using the acquired image of the real space; andprocessing circuitry configured toacquire an image of the real space including at least the medium having the handwringing of the user added,extract handwritten information from the image of the real space including at least the medium having the handwriting of the user added, andsuperimpose the extracted handwritten information on an image of the electronic data.2. The head mounted display according to claim 1 , wherein the processing circuitry is configured to compare the image of the real space including at least the medium having no handwriting of the user claim 1 , with the image of the real space including at least the medium having the handwriting of the user added to extract the handwritten information.3. The head mounted display according to claim 1 , whereinthe imaging device acquires a first image of the real space having at least no medium, and a second image of the real ...

Подробнее
Номер записи: 94
10-09-2015 дата публикации

EPULLTAB SYSTEM

Номер: US20150254504A1
Автор: Brown Jeffrey M., Macke Michael Mayo, Nizdil Mark Cameron
Принадлежит:

In one embodiment, a system comprising an epulltab comprising a win code, an encrypted code, and a bar code corresponding to the encrypted code; and a portal system comprising a first device at a first facility and a remote device coupled to the first device over a network, the remote device hosting a website, the first device providing a vendor interface to the website, the portal system configured to: receive the encrypted code or the bar code from the first facility; extract first information from the encrypted code or the bar code; compare at least a portion of the first information with a stored value; and determine whether to validate the epulltab based on the comparison. 1. A system , comprising:an epulltab comprising a win code, an encrypted code, and a bar code corresponding to the encrypted code; anda portal system comprising a first device at a first facility and a remote device coupled to the first device over a network, the remote device hosting a website, the first device enabling a vendor to interact with the website, the portal system configured to:receive the encrypted code or the bar code from the first facility;extract first information from the encrypted code or the bar code;compare at least a portion of the first information with a stored value; anddetermine whether to validate the epulltab based on the comparison.2. The system of claim 1 , wherein the portal system is configured to extract the first information by either decoding the bar code scanned by the first device to obtain the encrypted code claim 1 , and decrypting the encrypted code claim 1 , or decrypting the encrypted code that is entered manually by a user at the first device.3. The system of claim 2 , wherein the portal system is configured to decrypt by:segmenting a string of numbers into multiple segments;reordering the multiple segments;building a string based on the reordered segments;performing a checksum of the string;extracting a coordinate code, a batch number, and a tab ...

Подробнее
Номер записи: 95
09-09-2021 дата публикации

INTERACTIVE EDITING OF ELECTRONIC TEXT

Номер: US20210279458A1
Автор: Buckley Thomas William, Cirimele Maria, Karim Tayeb Al, Mickle Robert Ky
Принадлежит:

A new segment of electronic handwriting is provided to a handwriting recognition module to obtain a plurality of textual interpretations of the new segment. The textual interpretations obtained from the handwriting recognition module are scored based on how each respective electronic handwriting representation would change a display of existing electronic content when the respective electronic handwriting representation is displayed substantially at the user designated position within or adjacent to the existing electronic content. Based on the scoring, an electronic handwriting representation corresponding to a respective textual interpretation of the plurality of textual interpretations is selected, and the existing electronic content is modified to include the selected electronic handwriting representation located substantially at the user designated position. 120-. (canceled)21. A method comprising:determining, by a computing system and based on a segment of electronic handwriting, a plurality of candidate content segments;generating, by the computing system and based on the plurality of candidate content segments, a respective electronic handwriting representation for each candidate content segment from the plurality of candidate content segments;determining, by the computing system, a respective score for each of the plurality of candidate content segments based on a change in a display of existing electronic content if the respective electronic handwriting representation is displayed in place of the segment of the electronic handwriting;selecting, by the computing system and based on the respective scores, one of the plurality of candidate content segments as a selected electronic handwriting representation; andoutputting, for display on a display device, the selected electronic handwriting representation.22. The method of claim 21 , wherein the electronic handwriting representations includes one or more computer-replicated glyphs substantially in a ...

Подробнее
Номер записи: 96
31-08-2017 дата публикации

IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE STORAGE MEDIUM

Номер: US20170249294A1
Автор: EMORI Mototsugu
Принадлежит:

An image processing device includes a handwriting renderer, an image renderer, an external image renderer, a serializer, a creator, a recognizer, and a concatenation unit. The handwriting renderer is configured to render a stroke on a first layer. The image renderer is configured to render an image on a second layer lower than the first layer. The external image renderer is configured to render an external image on a third layer lower than the second layer. The serializer is configured to convert the stroke rendered on the first layer and the images rendered on the second and third layers into text data. The creator is configured to create document data corresponding to one page based on the text data. The recognizer is configured to acquire a character string from the stroke. The concatenation unit is configured to concatenate adjacent characters on the string with an unnecessary space therebetween being deleted. 1. An image processing device comprising:a handwriting image renderer configured to render a stroke on a first layer;an image renderer configured to render an image representing at least one of a character, a symbol, and a figure on a second layer lower than the first layer;an external image renderer configured to render an external image that is externally acquired on a third layer lower than the second layer;a serializer configured to convert the stroke rendered on the first layer, the image rendered on the second layer, and the external image rendered on the third layer into data in a text format;a document creator configured to create document data corresponding to one page based on the data in a text format converted by the serializer;a handwriting recognizer configured to perform character recognition processing on a character string image represented by the stroke to acquire a character string from the character string image; anda character concatenation unit configured to determine whether adjacent characters on the character string acquired by the ...

Подробнее
Номер записи: 97
23-09-2021 дата публикации

UTILIZING MACHINE LEARNING MODELS, POSITION BASED EXTRACTION, AND AUTOMATED DATA LABELING TO PROCESS IMAGE-BASED DOCUMENTS

Номер: US20210295103A1
Автор: Chen Jiayi, CHING Man Lok, GREEN Riley, HIGGINS Luke, KULKARNI Aditi, LEMA Reuben, Liu Xiaolei, MOORE Isabella Phoebe Groenewegen, SUN Xiwen, TANNIRU Rajendra Prasad, VIJAYARAGHAVAN Koushik M.
Принадлежит:

A device may receive image data that includes an image of a document and lexicon data identifying a lexicon, and may perform an extraction technique on the image data to identify at least one field in the document. The device may utilize form segmentation to automatically generate label data identifying labels for the image data, and may process the image data, the label data, and data identifying the at least one field, with a first model, to identify visual features. The device may process the image data and the visual features, with a second model, to identify sequences of characters, and may process the image data and the sequences of characters, with a third model, to identify strings of characters. The device may compare the lexicon data and the strings of characters to generate verified strings of characters that may be utilized to generate a digitized document. 1. A method , comprising:receiving, by a device, image data that includes an image of a document to be digitized and lexicon data identifying a lexicon associated with the document;performing, by the device, an extraction technique on the image data to identify at least one field provided in the document;utilizing, by the device, form segmentation to automatically generate label data identifying labels for the image data;processing, by the device, the image data, the label data, and data identifying the at least one field, with a convolutional neural network model, to identify visual features of the image data;processing, by the device, the image data and the visual features, with a recurrent neural network model, to identify sequences of characters in the image data;processing, by the device, the image data and the sequences of characters, with a connectionist temporal classification model, to identify strings of characters in the image data;comparing, by the device, the lexicon data and the strings of characters to verify the strings of characters and to generate verified strings of characters and ...

Подробнее
Номер записи: 98
08-09-2016 дата публикации

Ink experience for images

Номер: US20160259766A1
Автор: Ales Holecek, Ali Akgun, Maxim Kudryavtsev, Panos C. Panay, Sergei Ivanov
Принадлежит: Microsoft Technology Licensing LLC

Techniques for an ink experience with images are discussed herein. In various implementations, an image is displayed via an image management application for viewing and/or editing images. In conjunction with interaction scenarios provided via the application, an inking mode for adding inked annotations to the image is enabled. Input to apply one or more inked annotations to the image is obtained, such as via finger touches on a touchscreen, drawing with a stylus, camera-based gestures, or other natural input mechanisms. Responsive to obtaining the input, data blocks corresponding to the one or more inked annotations are appended to an image file as additional data blocks for the image.

Подробнее
Номер записи: 99
08-08-2019 дата публикации

SYSTEM AND METHOD FOR CLASSIFYING IMAGES OF AN EVIDENCE

Номер: US20190244046A1
Автор: Davidovits Natanel, GUZMAN Noam, SAFT Isaac
Принадлежит: Vatbox, Ltd.

A system and method for classifying images of an evidence, the method including: generating an unlabeled template based on a first received image, wherein the unlabeled template includes a first set of regions of interest (ROIs); selecting a labeled template that includes a second set of ROIs from a plurality of labeled templates determined to be a best match for the unlabeled template; checking at least an ROI of the first set of ROIs for content that corresponds to a label of an equivalent ROI of the second set of ROIs; and, classifying the first image upon determination that the content checked corresponds to the label according to the labeled template. 1. A method for classifying images of an evidence , the method comprising:generating an unlabeled template based on a first received image, wherein the unlabeled template includes a first set of regions of interest (ROIs);selecting a labeled template that includes a second set of ROIs from a plurality of labeled templates determined to be a best match for the unlabeled template;checking at least an ROI of the first set of ROIs for content that corresponds to a label of an equivalent ROI of the second set of ROIs; and,classifying the first image upon determination that the content checked corresponds to the label according to the labeled template.2. The method of claim 1 , further comprising:distinguishing between areas within the image that contain data elements and areas that do not contain data elements.3. The method of claim 1 , wherein selecting a first labeled template determined to be a best match for the unlabeled template is based at least on the content and position of the at least an ROI of the first set of ROIs.4. The method of claim 3 , wherein the best match is further based on identifying an array of ROIs claim 3 , where the array may be used to determine similarity between two or more labeled or unlabeled templates.5. The method of claim 1 , wherein checking the at least an ROI of the first set of ...

Подробнее
Номер записи: 100