СПОСОБ И СИСТЕМА ДЛЯ ОПРЕДЕЛЕНИЯ МЕСТОПОЛОЖЕНИЯ ВЫСОКОСКОРОСТНОГО ПОЕЗДА В НАВИГАЦИОННОЙ СЛЕПОЙ ЗОНЕ НА ОСНОВЕ МЕТЕОРОЛОГИЧЕСКИХ ПАРАМЕТРОВ

Изобретение относится к области вычислительной техники для определения местоположения поездов в тоннелях на основе метеорологических параметров. Технический результат заключается в повышении точности определения местоположения высокоскоростного поезда в навигационной слепой зоне на основе метеорологических параметров. Для этого заявлен способ, содержащий: получение метеорологических параметров тоннеля; классификацию полученных метеорологических параметров тоннеля; создание библиотеки шаблонов цветового пространства HSV типичной последовательности путем использования классифицированных метеорологических параметров тоннеля; обучение библиотеки шаблонов цветового пространства HSV типичной последовательности; обучение модели сопоставления шаблонов HSV; обучение модели распознавания RVM; создание модели объединения модели сопоставления шаблонов HSV и модели распознавания RVM, чтобы получить модель объединения предсказания пути в милях тоннеля; получение входных данных и вызов модели объединения ...

Display apparatus, display method, and display system

A display apparatus includes circuitry to receive an input of hand drafted data, display, on a display, an object corresponding to the hand drafted data and an external image that is externally input, perform character recognition on the hand drafted data to convert the hand drafted data into text data, and display, on the display, a search result obtained using at least a part of the external image and at least a part of the text data.

Text refinement network

MONITORING DEVICE OF ANALYZER

A monitoring device includes an acquisition unit configured to acquire a captured image of a display panel of a control device configured to control an analyzer, an image storage unit configured to store the captured image, and a state determination unit configured to determine a state of the analyzer based on the captured image.

Устройство для распознавания условно жестких деловых документов с автоматической привязкой их полей

Изобретение относится к информатике, а именно к устройствам для распознавания документов. Устройство для распознавания условно жестких деловых документов с автоматической привязкой их полей содержит модуль приема запросов пользователей, модуль селекции адресов записей идентификационных данных документов в базе данных сервера, модуль приема адресов записей идентификационных данных документов в базе данных сервера, модуль верификации данных реквизитов распознаваемых документов, модуль верификации контента распознаваемых документов, модуль приема идентификационных данных распознаваемых документов и транзакций из базы данных сервера и модуль выдачи транзакций пользователям, встроенный накопитель с энергонезависимой памятью, содержащий базу данных эталонных документов, и микропроцессор, выполненный с возможностью распознавания графических примитивов и их взаимного расположения на цифровом образе документа, а также сравнения эталонного и распознаваемого документов. Достигаемый технический результат ...

СПОСОБ РАСПОЗНАВАНИЯ ХИМИЧЕСКОЙ ИНФОРМАЦИИ ИЗ ИЗОБРАЖЕНИЙ ДОКУМЕНТОВ И СИСТЕМА ДЛЯ ЕГО ОСУЩЕСТВЛЕНИЯ

Изобретение относится к области вычислительной техники для распознавания данных. Техническим результатом является обеспечение автоматического распознавания из изображений документов химической информации, сокращение времени и повышение точности распознавания химической информации из изображений документов. Компьютерно-реализуемый способ включает следующие этапы: ввод изображения страницы документа в детектор; детектор идентифицирует фрагменты на странице; получение координат фрагмента на странице для каждого идентифицированного фрагмента; и классификация фрагментов; блок распознавания структуры распознает химическую структуру для каждого фрагмента; ввод идентифицированных фрагментов стрелок реакции в блок распознавания стрелок; получение координат на странице для каждой стрелки и атрибутов реакции; подачу на вход блока распознавания реакций координат на странице для каждого фрагмента распознанных химических структур; и на основании полученных данных блок распознавания реакций определяет ...

SURFACE PRESENTATIONS

Examples of computing devices are described herein. In some examples, a computing device includes machine-readable instructions stored in a non-transitory storage medium. In some examples, the instructions are executable by a processor to determine a content feed using artificial intelligence based on a captured image of a writing surface. In some examples, the instructions are executable to present the content feed with a representation of the writing surface.

SEARCH RESULTS WITHIN SEGMENTED COMMUNICATION SESSION CONTENT

Methods and systems provide for search results within segmented communication session content. In one embodiment, the system receives a transcript and video content of a communication session between participants, the transcript including timestamps for a number of utterances associated with speaking participants; processes the video content to extract textual content visible within the frames of the video content; segments frames of the video content into a number of contiguous topic segments; determines a title for each topic segment; assigns a category label for each topic segment; receives a request from a user to search for specified text within the video content; determines one or more titles or category labels for which a prediction of relatedness with the specified text is present; and presents content from at least one topic segment associated with the one or more titles or category labels for which a prediction of relatedness is present.

Text refinement network

After receiving an image 500 foreground text 550 is segmented from a background portion by classifying each pixel as text or background. A segmentation prediction 520 is produced using an additional convolutional layer. A key vector representing features such as texture of the text may be generated by applying a cosine similarity, bias, and softmax to the prediction. A neural network refines the prediction using the key vector. The image may be encoded using a ResNet architecture to produce a feature map 510 and decoded 515 to produce the segmentation prediction. Decoding may comprise applying a convolutional layer to the feature map, a first bias to an output of the layer, and a softmax to the output of the first bias. An attention map 530 and combined feature map 535 may be produced by combining the feature map and key vector. The key vector is generated 525 using a cosine similarity function, a second softmax, a second bias, and a pooling layer. The neural network is trained by segmenting ...

Methods for automatic number plate recognition systems

A method and system (1, fig.1) for automatic number plate recognition (ANPR). A plurality of images of vehicles (6, fig.1) with visible number plates are captured. An algorithm determines probabilities that one or more symbols on the number plates have been correctly recognised based on confidence values associated with the symbols. The accuracy of the ANPR system is estimated based on the probabilities. An alert may be issued or maintenance may be scheduled on the system if the accuracy is below a predetermined threshold. The method may be carried out on images captured during a first time-period (402 fig.4) and then repeated with images captured in a second time period (404 fig.4) to determine a change in accuracy. An alert may be issued or maintenance may be scheduled if the change in accuracy is greater than predetermined thresholds. The probability of correct symbol recognition may be calculated using a machine learning model trained to output a probability of accurate recognition ...

Action recognition method and device for target object, and electronic apparatus

An action recognition method and device for a target object, and an electronic apparatus. The action recognition method for a target object comprises: obtaining an original image from an image source, the original image comprising a target object (S101); recognizing the target object from the original image (S102); detecting a plurality of key points of the target object (S103); determining, on the basis of the detected key points, visibility attributes of the plurality of key points, wherein the visibility attributes are used to indicate whether or not the key points are occluded (S104); and recognizing an action of the target object according to a combined value of the visibility attributes of the plurality of key points (S105). The method uses visibility of key points to determine actions of a target object, thereby resolving the technical issue in the prior art in which complex actions cannot be accurately recognized.

SYSTEMS AND METHODS FOR REMEDIATING CHANGES IN ITEM LISTING DATA

The disclosed technology provides for implementing remediations to item listing data in an online retail environment. A method can include receiving, by a computing system from a data management system, a topic for a change in item listing data, retrieving, from a data store, at least one model trained to (i) identify changes in other item listing data, (ii) determine at least one suggested remediation to the changes to generate accurate item listing data, and (iii) determine at least one confidence metric indicating a likelihood that the at least one suggested remediation will result in generating the accurate item listing data, inputting the item listing data to the at least one model, receiving output from indicating at least one suggestion to remediate the item listing data, determining that the at least one suggestion satisfies auto-remediation criteria, and auto-remediating the item listing data with the at least one suggestion.

Systems, devices, and methods for software coding

Methods and systems described herein allow dynamic rendering of a reflexive questionnaire based on a modifiable spreadsheet for users with little to no programming experience and knowledge. The method and system allow retrieving a spreadsheet to generate a dynamic and reflexive graphical user interface and to pre-populate one or more input elements within the reflexive graphical user interface based on user information retrieved from a disparate data source, where the spreadsheet may be configured for a worksheet inheritance or where the worksheet may be accessed through a check-in/check-out functionality.

ELECTRONIC APPARATUS FOR DISPLAYING IMAGE AND OPERATING METHOD THEREOF

Disclosed is an electronic apparatus including a display, a memory configured to store at least one instruction, and at least one processor configured to execute the at least one instruction stored in the memory to obtain input documents, recognize, an element comprising at least one of a character, an image, or a combination of the character and the image; classify a type of each of the input documents based on a kind of the recognized element, and obtain calibration documents by arranging the recognized elements in a row based on the classified type of each of the input documents; and control the display to display the obtained calibration documents.

USER INTERFACES FOR MANAGING VISUAL CONTENT IN MEDIA

The present disclosure generally relates to methods and user interfaces for managing visual content at a computer system. In some embodiments, methods and user interfaces for managing visual content in media are described. In some embodiments, methods and user interfaces for managing visual indicators for visual content in media are described. In some embodiments, methods and user interfaces for inserting visual content in media are described. In some embodiments, methods and user interfaces for identifying visual content in media are described. In some embodiments, methods and user interfaces for translating visual content in media are described. In some embodiments, methods and user interfaces for translating visual content in media are described. In some embodiments, methods and user interfaces for managing user interface objects for visual content in media are described.

Motion prediction with ego motion compensation and consideration of occluded objects

The invention relates to a method for prediction of a motion of an object (7) in the environment of a vehicle (1), the method comprising: collecting sensor data of the object (7) in the environment of the vehicle (1) by at least one vehicle sensor and predicting the motion of the object (7) on the basis of the sensor data by a self-learning system (6), characterized by inputting occlusion data (8, 13) into the self-learning system (6), wherein the occlusion data (8, 13) refer to occluded objects of the environment, which are hidden for the at least one vehicle sensor and/or inputting ego motion data (16) into the self-learning system (6), wherein the ego motion data (16) refer to an ego motion of the vehicle (1), so that the motion of the object (7) is predicted taking into account the occluded objects and/or the ego motion of the vehicle (1). Also provided is a method of controlling an autonomous vehicle based on the prediction.

System and Method for Internal Etching of Transparent Materials with Information Pertaining to a Blockchain

In one embodiment, a system includes a piece of jewelry comprising an attached transparent gemstone. The transparent gemstone may be internally etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address.

ADJUSTING AN AUDIO TRANSMISSION WHEN A USER IS BEING SPOKEN TO BY ANOTHER PERSON

A method for adjusting an audio transmission when a user of the system is being spoken to by another person includes receiving audio signals representative of sounds from an environment of the user captured by at least one microphone; determining at least from the received audio signals that the another person is speaking to user; and subject to the user being spoken to by the another person, adjusting the audio transmission to the user and signaling to the user that the user is being spoken to.

METHOD AND APPARATUS FOR RECOGNIZING TEXT, STORAGE MEDIUM, AND ELECTRONIC DEVICE

A text recognition method and apparatus, a storage medium, and an electronic device. Said method comprises: acquiring a text image (S101); determining at least one text box from the text image, each text box corresponding to at least one word (S102); determining, from the at least one text box, a text box to be recognized (S103); determining, from the text image, a picture unit corresponding to the text box to be recognized (S104); rotating the picture unit to a target pose (S105); and performing text recognition on the picture unit in the target pose, and acquiring a target recognition result (S106). The method, apparatus, storage medium, and electronic device can recognize a text unit in a text having a large inclination angle.

METHODS AND SYSTEMS FOR WATERMARKING DOCUMENTS

Described are methods and system that digitally watermark documents using an encoding scheme that embeds unique identifiers into the files by perturbing the relative heights of words to create patterns that are imperceptible to the human eye but decodable to recover the identifiers. The unique identifiers can be precoded before they are embedded in the documents.

AUTOMATED TESTING OF MOBILE DEVICES USING BEHAVIORAL LEARNING

Described herein are techniques that may be used to automate testing of services on mobile devices using visual analysis. In some embodiments, a behavioral model or other machine learning model is trained using training data collected while testers use mobile devices to test the services. During execution of a testing routine on a mobile device, screenshots are obtained of a screen of the mobile device and provided to the machine learning model. The behavioral model or other machine learning model can use the provided screenshot to determine an action that simulates a user action (e.g., a user touch on the screen of the mobile device) at a location of an icon or other visual element associated with the testing routine. These steps are repeated until an end-state of the testing routine is detected. 1. A computer-implemented method , comprising:receiving, during a testing routine associated with a user goal on a mobile device, a screenshot of the mobile device; the behavioral model comprises a machine learning model trained on a set of training data indicating behavior of one or more users to achieve the user goal on one or more test devices, and', 'selection of the object is predicted, by the behavioral model, to cause progress towards achievement of the user goal on the mobile device; and, 'dynamically determining, using a behavioral model, an object shown in the screenshot to select with a simulated user action, whereincausing selection of the object on the mobile device.2. The computer-implemented method of claim 1 , wherein the behavioral model comprises:an object detector configured to identify, based on the screenshot, at least one of boundaries or coordinates of one or more objects shown in the screenshot;an optical character recognition (OCR) model configured to recognize text associated with the one or more objects; andan action prediction model configured to dynamically determine the object to select, from among the one or more objects.3. The computer- ...

Map representation data processing device, information processing method, and program

It is possible to realize navigation that employs map representation data acquired using a captured map photograph, with a map representation data processing device including: a photograph reception unit that receives a map photograph from a terminal device; a determination unit that searches a navigation information group that contains two or more pieces of navigation information that contain map representation data and two or more pieces of correspondence information that are each a set of coordinate information and position information on the map representation data, and determines a piece of navigation information that has a relationship that satisfies a first condition, with the map photograph; and a navigation information transmission unit that transmits the piece of navigation information determined by the determination unit, to the terminal device.

Control system for railway yard and related methods

A control system is for a railway yard with railroad tracks. The control system may include RCLs and sets of railcars on the railroad tracks. The control system may include railyard sensors configured to generate railyard sensor data of the railroad tracks, and a server in communication with the RCLs and the railyard sensors. The server may be configured to generate a database associated with the sets of railcars based upon the railyard sensor data. The database may have, for each railcar, a railcar type value, a railcar logo image, and a vehicle classification value. The server may be configured to selectively control the RCLs to position the sets of railcars within the railroad tracks based upon the railyard sensor data.

METHOD AND APPARATUS FOR DISPATCHING TO A GEO-LOCATION

An approach for receiving a request for dispatching to a physical site for delivery of an item is disclosed, wherein the physical site includes a personal identifier. The approach involves determining location information for the physical site wherein the location information includes address of a destination area that encompasses the physical site. The approach also involves generating a dispatch message to instruct a dispatcher to travel to the destination area according to the determined location to deliver the item. The approach further involves receiving a geo-tagged image of the physical site as verification of the physical site and the personal identifier. The approach also involves extracting textual information from the geo-tagged image, and determining that the textual information corresponds to the personal identifier. Further, the approach involves initiating update of the location information with geo-location information of the geo-tagged image, and storage of the geo-tagged ...

Search results within segmented communication session content

Methods and systems provide for search results within segmented communication session content. In one embodiment, the system receives a transcript and video content of a communication session between participants, the transcript including timestamps for a number of utterances associated with speaking participants; processes the video content to extract textual content visible within the frames of the video content; segments frames of the video content into a number of contiguous topic segments; determines a title for each topic segment; assigns a category label for each topic segment; receives a request from a user to search for specified text within the video content; determines one or more titles or category labels for which a prediction of relatedness with the specified text is present; and presents content from at least one topic segment associated with the one or more titles or category labels for which a prediction of relatedness is present.

System and method for etching internal surfaces of transparent gemstones with information pertaining to a blockchain

In one embodiment, a system including a tangible token comprising a single integrated transparent gemstone produced by fusing together a first transparent gemstone and a second transparent gemstone, a first internal side of the first transparent gemstone is etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address, the first internal side of the first transparent gemstone is aligned with a second internal side of the second transparent gemstone, and the aligning encapsulates the information within a perimeter of the second internal side such that the information does not extend beyond the perimeter. The system includes a computing device that executes instructions to: read the information, validate, via a network and the address, the public key and private key are associated with the blockchain, and present an indication of whether or not the information is validated.

STORAGE SPACE OPTIMIZATION FOR EMAILS

In some implementations, a storage optimization system may receive a plurality of emails. Accordingly, the system may identify at least one email associated with a limited capacity in the plurality of emails. The system may further scan, from the at least one email, one or more hyperlinks to determine a website associated with the at least one email and an identifier associated with an event. The system may determine, using a database, a traversal path and at least one application programming interface (API) call associated with the website. Accordingly, the system may traverse the website using the traversal path and the at least one API using the identifier to determine that the limited capacity is filled. The system may delete the at least one email associated with the limited capacity based on determining that the limited capacity is filled.

INTERACTIVE INFORMATION PROCESSING METHOD, DEVICE AND MEDIUM

Disclosed are an interactive information processing method, an electronic device and a storage medium. The method includes establishing a position correspondence between a display text generated based on a multimedia data stream and the multimedia data stream; and presenting the display text and the multimedia data stream corresponding to the display text based on the position correspondence.

SEARCH DEVICE, SEARCH METHOD, AND RECORDING MEDIUM

According to one embodiment, a CPU generates, based on a tone-marked pinyin search character string containing a wildcard “?” and acquired from a communication terminal, a tone-number-added pinyin search character string for wildcard search in which “0” is added to a character having no tone number (i.e., an alphabetical letter representing a consonant) and a tone number wildcard “?” is added to a position immediately after the existing wildcard “?”. The CPU also generates a tone-number-added pinyin entry word character string for wildcard search, by adding “0” to a character having no tone number in a tone-number-added pinyin entry word character string corresponding to a Chinese-Japanese dictionary entry word that matches a tone-number-omitted pinyin search character string. The CPU then compares the tone-number-added pinyin search character string for wildcard search with the tone-number-added pinyin entry word character string for wildcard search to determine if they match each other ...

Interactive information processing method, device and medium

Disclosed are an interactive information processing method, an electronic device and a storage medium. The method includes establishing a position correspondence between a display text generated based on a multimedia data stream and the multimedia data stream; and presenting the display text and the multimedia data stream corresponding to the display text based on the position correspondence.

STRUCTURING UNSTRUCTURED DATA VIA OPTICAL CHARACTER RECOGNITION AND ANALYSIS

The present disclosure describes devices and methods of providing a technology environment for analyzing unstructured data to generate structured data. A set of electronic documents, each electronic document associated with a type of product, may be accessed. A data instance for each of the documents may be generated. The data instance may include a plurality of data fields that are based on the type of product. The electronic documents may be analyzed to identify values for each of the plurality of data fields. Analyzing the electronic documents may comprise applying a respective character recognition algorithm to respective electronic documents, and assigning a confidence factor to each of the values. The data instances comprising the values for each of the plurality of data fields may be stored in a second database.

Chat attachment screening

Certain aspects of the present disclosure provide techniques and systems for screening chat attachments. A chat attachment screening system monitors a chat window of a first computing device associated with a first user during an interaction session between the first user and a second user. An upload of an attachment is detected based on the monitoring. Access to the attachment from a second computing device associated with the second user is blocked, in response to detecting the upload. Content from the attachment is identified and extracted. A type of the attachment is determined based on the content. A determination is made as to whether the second user is authorized to access the type of the attachment. An indication of the determination is presented on at least one of the first computing device or the second computing device during the interaction session.

POSITION DETECTION DEVICE, POSITION DETECTION METHOD, AND STORAGE MEDIUM STORING POSITION DETECTION PROGRAM

A position detection device includes processing circuitry: to receive an image captured by a monitoring camera, to execute a process for detecting a person in the image, and to output two-dimensional camera coordinates indicating a position of the detected person; to transform the two-dimensional camera coordinates to three-dimensional coordinates; to recognize a character string on a nameplate of a device in a wearable camera image captured by a wearable camera; to search a layout chart of the device for the recognized character string; to determine two-dimensional map coordinates based on a position where the character string is found when the recognized character string is found in the layout chart, and to calculate the two-dimensional map coordinates based on the three-dimensional coordinates when the recognized character string is not found in the layout chart; and to output image data in which position information is superimposed on a map.

VIDEO-BASED CHAPTER GENERATION FOR A COMMUNICATION SESSION

Methods and systems provide for providing video-based chapter generation for a communication session. In one embodiment, the system receives a transcript and video content of a communication session between participants, the transcript including timestamps for a number of utterances associated with speaking participants; processes the video content to extract one or more pieces of textual content visible within the frames of the video content; segments frames of the video content into a number of contiguous topic segments; determines a title for each topic segment from one or more of: the transcript, and the extracted textual content; assigns a category label for each topic segment from a prespecified list of category labels; and transmits, to one or more client devices, the list of topic segments with determined title and assigned category label for each of the merged topic segments.

INSPECTION APPARATUS AND STORAGE MEDIUM STORING COMPUTER PROGRAM

An inspection apparatus acquires drawing data indicating a drawing of a portion including a label affixed to a particular affix position of a product, identifies the label in the drawing, identifies a position of a reference portion of the product in the drawing, acquires dimension information indicated in the drawing based on the drawing data and identification results of the label and the reference portion in the drawing, acquires captured image data obtained by capturing an image of the product, identifies the label in the captured image, identifies the reference portion of the product in the captured image, and determines whether an affix position of the label in the captured image is the particular affix position specified by the dimension information, based on identification results of the label and a position of the reference portion in the captured image and the dimension information.

System and Method for Internal Etching of Transparent Materials with Information Pertaining to a Blockchain

In one embodiment, a system includes a tangible token comprising a transparent gemstone. The transparent gemstone may be internally etched with information pertaining to a blockchain, and the information includes at least a private key, a public key, and an address. The information may pertain to a cryptocurrency transaction instruction stored on the blockchain.

Image reading apparatus comprising a processor that detects an abnormal pixel, and outputs an image obtained by a first processing or second processing based on if character recognition processing of a character obtained by first processing is the same as the character obtained by the second processing

An image reading apparatus includes a conveyance unit configured to convey an original; a reading unit comprising a reading sensor, the reading sensor having a light receiving element to receive light of a first color and a light receiving element to receive light of a second color that is different from the first color, wherein the reading unit is configured to read an image of the original conveyed by the conveyance unit by using the reading sensor to generate image data which represents a reading result of the reading unit; at least one processor configured to: determine a first abnormal position that is a position in a first direction of an abnormal pixel of the first color in an image represented by the image data.

DOCUMENT PROCESSING

A method of document processing is provided. An implementation solution is: obtaining target text information and target layout information of a target document, the target text information includes target text included in the target document and character position information of the target text, and the target layout information is used to characterize the region where text in the target document is located; fusing the target text information and the target layout information to obtain first multimodal information of the target document; and inputting the first multimodal information into an intelligent document comprehension model, and obtaining at least one target word in the target document and at least one feature vector corresponding to the at least one target word output by the intelligent document comprehension model, each target word is related to semantics of the target document.

Machine Learning Based Document Visual Element Extraction

A method includes obtaining a document with textual fields and a visual element. For each textual field, the method includes determining a textual offset for the textual field that indicates a location of the textual field relative to each other textual field in the document. The method includes detecting, using a machine learning vision model, the visual element and determining a visual element offset indicating a location of the visual element relative to each textual field in the document. The method includes assigning the visual element a visual element anchor token and inserting the visual element anchor token into the textual fields in an order based on the visual element offset and the respective textual offsets. The method also includes, after inserting the visual element anchor token, extracting, using a text-based extraction model, from the textual fields, structured entities representing the series of textual fields and the visual element.

AUTOMATIC STATE ASSIGNMENT TO DOCUMENTS BASED ON PHRASE OCCURRENCE IN TEXT

Fuzzy document state assignment includes loading into memory a raster image of a document and performing OCR upon a page of a document in order to produce parseable text. The parseable text is then segmented and normalized and an index is generated from the segmented and normalized text. Thereafter, a probability of a particular classification is computed based upon the detection in the index of a combination of words associated with a corresponding classification. Finally, the document is annotated with the particular classification.

INTERACTIVE INFORMATION PROCESSING METHOD, DEVICE AND MEDIUM

Disclosed are an interactive information processing method, an electronic device and a storage medium. The method includes establishing a correspondence between a multimedia data stream and a display text generated based on the multimedia data stream; presenting the multimedia data stream and the display text based on the correspondence; and in response to detecting a triggering operation triggering a display content in the display text, adjusting, based on a timestamp corresponding to the display content and the correspondence, the multimedia data stream to navigate to a playback position corresponding to the display content; the display content comprises a text corresponding to speech in the multimedia data stream; and the display text and the multimedia data stream are displayed on different display areas of a page respectively, and a display area occupied by the display text is not superimposed on a display area occupied by the multimedia data stream.

AR TRANSLATION PROCESSING METHOD AND ELECTRONIC DEVICE

Provided are an AR translation processing method and an electronic device, which relate to the technical field of communications. By the method, in a scenario in which an electronic device is used for AR translation, a pose change of the electronic device can be detected in real time, and feature matching can be performed on a plurality of consecutive frames of images acquired by a camera, so that whether to-be-translated text needs to be fully translated or partially translated, or needs not to be translated can be determined based on the pose change of the electronic device and a feature matching result, and therefore a corresponding translation trigger strategy is selected. In this way, repeated translation can be effectively avoided, thereby saving computing resources in the AR translation process and improving the translation efficiency to a particular extent.

IMAGE READING APPARATUS

An image reading apparatus includes a conveyance unit configured to convey an original; a reading unit comprising a reading sensor, the reading sensor having a light receiving element to receive light of a first color and a light receiving element to receive light of a second color that is different from the first color, wherein the reading unit is configured to read an image of the original conveyed by the conveyance unit by using the reading sensor to generate image data which represents a reading result of the reading unit; at least one processor configured to: determine a first abnormal position that is a position in a first direction of an abnormal pixel of the first color in an image represented by the image data.

SYSTEM AND METHOD FOR GENERATING ACCESSIBLE USER EXPERIENCE DESIGN GUIDANCE MATERIALS

A system and method for generating accessible user experience (UX) design guidance materials for software products uses page elements that are optically extracted from an input UX prototype page image and automatically classified into predefined element types to find accessibility rules for at least some of the extracted page elements. At least one accessible UX design guidance material is generated for the input UX prototype page image that indicates the extracted page elements and the accessibility rules corresponding to at least some of the extracted page elements.

ELECTRONIC DEVICE AND CONTROL METHOD OF SAME

An electronic device and a method thereof are provided. The electronic device includes: a memory and a processor configured to: acquire feature data of a plurality of images in a video using a first artificial neural network of a first artificial intelligence model; acquire a plurality of key frames of the video based on the feature data of the plurality of images using a second artificial neural network of the first artificial intelligence model; acquire first feature data of remaining key frames excluding at least one of the plurality of key frames using a first artificial neural network of a second artificial intelligence model; acquire second feature data including information about relationships between the remaining key frames based on the first feature data using a second artificial neural network of the second artificial intelligence model; and acquire texts for the plurality of key frames based on the second feature data.

DIRECT PART MARKING CODE READING WITH MULTIMODAL OBJECT SENSING

An optical symbol reading system comprises an image sensor operative to capture an image of a target area, a color-sensing system sensitive to certain colors in the visible spectrum, an illumination system operative to produce various types of illumination based on illumination parameters, and a surface-profiling system arranged to measure distance to multiple points of at least one surface in the target area. The illumination system, the image sensor, and the color-sensing system are arranged such that emitted light from the illumination system, in accordance with a selected type of illumination, is directed towards the target area while a portion of the emitted light is reflected from any object of interest present in the target area and received by the image sensor and the color-sensing system. The type of illumination is selected based on output from the color-sensing system and the surface-profiling system.

Storage space optimization for emails

In some implementations, a storage optimization system may receive a plurality of emails. Accordingly, the system may identify at least one email associated with a limited capacity in the plurality of emails. The system may further scan, from the at least one email, one or more hyperlinks to determine a website associated with the at least one email and an identifier associated with an event. The system may determine, using a database, a traversal path and at least one application programming interface (API) call associated with the website. Accordingly, the system may traverse the website using the traversal path and the at least one API using the identifier to determine that the limited capacity is filled. The system may delete the at least one email associated with the limited capacity based on determining that the limited capacity is filled.

System and method for internal etching surfaces of transparent materials with information pertaining to a blockchain

In one embodiment, a system including a tangible token comprising a single integrated transparent gemstone produced by fusing together a first transparent gemstone and a second transparent gemstone, a first internal side of the first transparent gemstone is etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address, the first internal side of the first transparent gemstone is aligned with a second internal side of the second transparent gemstone, and the aligning encapsulates the information within a perimeter of the second internal side such that the information does not extend beyond the perimeter. The system includes a computing device that executes instructions to: read the information, validate, via a network and the address, the public key and private key are associated with the blockchain, and present an indication of whether or not the information is validated.

Systems and methods to enhance early detection of performance induced risks for an autonomous driving vehicle

Systems and methods of adjusting zone associated risks of a coverage zone covered by one or more sensors of an autonomous driving vehicle (ADV) operating in real-time are disclosed. As an example, the method includes defining a performance limit detection window associated with a first sensor based on a mean time between failure (MTBF) lower limit of the first sensor and a MTBF upper limit of the first sensor. The method further includes determining whether an operating time of the ADV operating in autonomous driving (AD) mode is within the performance limit detection window associated with the first sensor. The method further includes in response to determining that the operating time of the ADV operating in AD mode is within the performance limit detection window of the first sensor, adjusting a zone associated risk of the coverage zone to a performance risk of a second sensor.

Systems and methods for pattern-based multi-stage deterministic data classification

Systems and methods for pattern-based multi-stage deterministic data classification that may reduce processing and memory overhead while providing more accurate data classifications.

METHOD AND SYSTEM FOR PACKAGE MOVEMENT VISIBILITY IN WAREHOUSE OPERATIONS

Present disclosure provides a method and system for package movement visibility in warehouse operations. The method includes identifying, by the package management system (1000), an object entering AOE and moving in a predetermined direction and recording, by the package management system (1000), image frame of the object. The method also includes determining, by the package management system (1000), that the object in the image frame is a package and determining, by the package management system (1000), a label on the package from the image frame. Further, the method also includes determining, by the package management system (1000), a match to the label in a cloud platform (400) and sending, by the package management system (1000), tracking details associated with the package based on the match to the label in the cloud platform (400), to a client device in real-time.

Method for determining search region using region information and object information and system performing the same

Embodiments relate to a method for determining a search region including acquiring object information of a target object included in an image query, generating a set of non-image features of the target object based on the object information, setting a search candidate region based on a user input, acquiring information associated with the search candidate region from a region database, and determining a search region based on at least one of the information associated with the search candidate region or at least part of the set of non-image features, and a system for performing the same.

Systems and methods for classifying documents

A system may iteratively scan a portion of a document, extract first data from the portion of the document, and determine, using a trained model, whether the first data corresponds to one or more document types based on one or more confidence thresholds. The system may repeat this process, increasing the portion of the document scanned by a predetermined amount each iteration, until the first data corresponds to the one or more document types based on the one or more confidence thresholds. Responsive to determining the first data corresponds to the one or more document types based on the one or more confidence thresholds, the system may cause a graphical user interface (GUI) of a user device to display a notification indicating a document type match.

User interfaces for managing visual content in media

The present disclosure generally relates to methods and user interfaces for managing visual content at a computer system. In some embodiments, methods and user interfaces for managing visual content in media are described. In some embodiments, methods and user interfaces for managing visual indicators for visual content in media are described. In some embodiments, methods and user interfaces for inserting visual content in media are described. In some embodiments, methods and user interfaces for identifying visual content in media are described. In some embodiments, methods and user interfaces for translating visual content in media are described. In some embodiments, methods and user interfaces for translating visual content in media are described. In some embodiments, methods and user interfaces for managing user interface objects for visual content in media are described.

AGNOSTIC IMAGE DIGITIZER

Methods for enhancing compatibility of a document of an entity with an organization's database on a computer server. Methods may include using a computer hardware processor to digitize a document from a first format into a digital format, such as bytes, when the first format may not be compatible with the database. Methods may further include using a computer hardware processor to convert the document from a digital format into a second format, where the second format of the document may be compatible with the organization's database. Methods may include using a computer hardware processor to populate the database on the computer server with data from the document in the second format. Methods may further include storing the populated database and the document in the second format on the computer server.

Agnostic image digitizer

Methods for enhancing compatibility of a document of an entity with an organization's database on a computer server. Methods may include using a computer hardware processor to digitize a document from a first format into a digital format, such as bytes, when the first format may not be compatible with the database. Methods may further include using a computer hardware processor to convert the document from a digital format into a second format, where the second format of the document may be compatible with the organization's database. Methods may include using a computer hardware processor to populate the database on the computer server with data from the document in the second format. Methods may further include storing the populated database and the document in the second format on the computer server.

METHOD AND A SYSTEM FOR FILLING VEHICLE TIRES WITH PRESSURIZED AIR

In-vehicle monitoring information generation control device and in-vehicle monitoring information generation control method

An in-vehicle monitoring information generation control device includes: an image acquisition unit acquiring an image generated by capturing the inside of an unmanned vehicle; an abnormality determination unit determining whether or not an abnormality is occurring in the unmanned vehicle; an in-vehicle monitoring information generating unit generating in-vehicle monitoring information, with which no passenger in the unmanned vehicle who is captured in the image can be identified, on the basis of the image acquired by the image acquisition unit; and a transmission control unit transmitting the in-vehicle monitoring information generated by the in-vehicle monitoring information generating unit to the outside of the unmanned vehicle in a case where it is determined that no abnormality is occurring in the unmanned vehicle on the basis of a determination result determined by the abnormality determination unit.

SYSTEM AND METHOD FOR AUTOMATIC VIDEO RECONSTRUCTION WITH DYNAMIC POINT OF INTEREST

INFORMATION PROCESSING DEVICE AND METHOD, AND PROGRAM

The present disclosure relates to an information processing device and method, and a program that enable processing corresponding to a recognition result with respect to a license plate of a vehicle. On the basis of a recognition result with respect to a license plate of a vehicle in a captured image, characteristic information of the vehicle is extracted from the captured image, and processing corresponding to the extracted characteristic information of the vehicle is performed. The present disclosure can be applied to, for example, an information processing device, an image processing device, a communication device, an electronic apparatus, an information processing method, a program, or the like.

SYSTEMS AND PROCESSES FOR TEXT EXTRACTION AND ANALYSIS

A system can include a data store, including a subscriber list, and a computing device in communication therewith. The computing device can perform optical character recognition of an image to identify text portions, each text portion including position data and a subset of text portions including handwritten data. The computing device can associate each text portion with a respective column of a plurality of columns and a respective row of a plurality of rows based on the position data. The computing device can analyze individual ones of text portions associated with a particular column to determine a particular data type corresponding to the particular column. The computing device can generate a respective entry to the subscriber list for individual ones of a subset of the plurality of rows with individual ones of the text portions from the particular column being stored in a field associated with the particular data type.

Copying Shared Content Using Machine Vision

Selections of content shared from a remote device during a video conference are copied to a destination of a computing device connected to the video conference live or at which a recording of the video conference is viewed. The content shared from the remote device during the video conference is output at a display of the computing device. A portion of the content is selected according to an instruction received from a user of the computing device while output at the display of the computing device to copy to a destination associated with software running at the computing device. The portion of the content is identified using a machine vision process performed against the content while output at the display of the computing device. The portion of the content is then copied to the destination.

Immunization Management System and Method

A system includes a computing device to receive medical information associated with a particular patient, compare immunization records for the particular patient with a recommended immunization schedule for the particular patient and determine that there is at least one immunization to be scheduled for the particular patient, schedule the at least one immunization for the particular patient based on at least one factor comprising a spoken language of the particular patient, a location of the particular patient, and acceptance of insurance for the particular patient for a healthcare provider, and generate an alert in realtime for the healthcare provider when the particular patient arrives at the healthcare provider for the at least one immunization scheduled for the particular patient.

Geofence-based object identification in an extended reality environment

A mobile device that includes a camera and an extended reality software application program is employed by a user in an operating environment, such as an industrial environment. One or more objects within a geofence may be identified. A device crosses within the geofence and acquires sensor data associated with an object within the geofence. The sensor data may include image data and/or audio data. The device or a server system may then determine an object identifier associated with the object based on a comparison of the sensor data with data associated with object identifiers corresponding to objects within the geofence. Based on the object identifier, data associated with the object are obtained. The data associated with the object may be presented via the device, such as an extended reality overlay over a view of the object in the device.

INTERFACE INFORMATION PROCESSING METHOD AND APPARATUS, STORAGE MEDIUM, AND DEVICE

An interface information processing method and apparatus, a storage medium, and a device are provided. The method includes: displaying, based on a trigger operation on a floating translation component in a first display interface, a trigger progress in the floating translation component, the first display interface including a character of a first language type, the trigger progress being associated with trigger duration, and the trigger duration being a duration of the trigger operation on the floating translation component; and switching the first display interface to a second display interface based on the trigger progress in the floating translation component satisfying a full-screen translation start progress, the second display interface including a character of a second language type, and the character of the second language type being obtained by translating the character of the first language type.

System and Method for Internal Etching Surfaces of Transparent Materials with Information Pertaining to a Blockchain

In one embodiment, a system includes a tangible token comprising a transparent gemstone, wherein: the transparent gemstone is internally etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address, and the information is represented as a quick response code. The system includes a computing device configured to execute instructions that cause the computing device to: read the information, and validate, via a network and the address, the public key and the private key are associated with at least one block on the blockchain.

Interface information processing method and apparatus, storage medium, and device

An interface information processing method and apparatus, a storage medium, and a device are provided. The method includes: displaying, based on a trigger operation on a floating translation component in a first display interface, a trigger progress in the floating translation component, the first display interface including a character of a first language type, the trigger progress being associated with trigger duration, and the trigger duration being a duration of the trigger operation on the floating translation component; and switching the first display interface to a second display interface based on the trigger progress in the floating translation component satisfying a full-screen translation start progress, the second display interface including a character of a second language type, and the character of the second language type being obtained by translating the character of the first language type.

System and Method for Internal Etching of Transparent Materials with Information Pertaining to a Blockchain

In one embodiment, a system includes a tangible token comprising a transparent gemstone, wherein the transparent gemstone is internally etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address. The system includes a computing device configured to execute instructions that cause the computing device to: read the information, and validate, via a network and the address, the public key and the private key are associated with at least one block on the blockchain.

Login method based on fingerprint recognition and device

A fingerprint recognition method and terminal device provide authentication by simultaneously collecting fingerprint data when a power-on signal is detected, attempting to match the fingerprint data with preset fingerprint data, and logging in to the terminal device proceeds when the matching succeeds.

Systems and methods for managing private information

The present disclosure relates to methods and systems for measuring private information protection across a number of external services. A centralized private information protection service is coupled to external services, accesses data of these external services, aggregates the data and determines a private information protection scoring based upon the aggregated data.

Metadata-based diarization of teleconferences

A method for audio processing includes receiving a recording of a teleconference among multiple participants over a network, including an audio stream containing speech uttered by the participants and information outside the audio stream. The method further includes processing the audio stream to identify speech segments interspersed with intervals of silence, extracting speaker identifications from the information outside the audio stream in the received recording, labeling a first set of the identified speech segments from the audio stream with the speaker identifications, extracting acoustic features from the speech segments in the first set, learning a correlation between the speaker identifications labelled to the segments in the first set and the extracted acoustic features, and labeling a second set of the identified speech segments using the learned correlation, to indicate the participants who spoke during the speech segments in the second set.

SYSTEM AND METHOD FOR DETERMINING ONE OR MORE CODES OF CAN BUS MESSAGES BASED PARTLY ON CAMERA CAPTURED IMAGES

A system for determining codes of vehicle's Can-bus dashboard messages, each message being associated with a dashboard notification, comprising: (a) a message generator sequentially generating on the Can-bus different message codes selected from a reduced space from the Message-ID and the Data fields; (b) a message storage for storing each generated message code, together with its timestamp; (c) a camera capturing an image of the dashboard, in synchronization with each message generation; (d) an images storage storing images captured by the camera, each image with its respective timestamp; (e) a processor configured to (i) compare each captured image with a latest previously captured image within the storage; (ii) when a difference is found between any captured image and a latest previously captured image, and based on the image timestamp, associate the later captured image with the code of the respective generated message in said message storage having the same timestamp.

SYSTEM AND METHOD FOR OCR-BASED TEXT CONVERSION AND COPYING MECHANISM FOR AGENTLESS HARDWARE-BASED KVM

The present disclosure relates to a method for selecting and copying one or more characters of at least one of text or alphanumeric information appearing within a video image frame being displayed on a display of a client computing device, during a keyboard, video and mouse (KVM) session with a remote KVM appliance. The method enables a user to define text or alphanumeric information being displayed in a video frame on the display, using a control component of the client computing device, which the user desires to convert into text. The method uses an optical character recognition (OCR) software application to convert the selected video information into a text output. The text output can then be copied and pasted into one or more other applications, documents or web pages by the user for subsequent use.

AMBIENT ENVIRONMENT INFORMATION TRANSMISSION DEVICE

... [Problem] Provided is an ambient environment information transmission device capable of quickly and accurately transmitting ambient environment information to a visually impaired person. [Solution] An ambient environment information transmission device 1 includes a body 10 that is configured to be worn by a user, a distance image capturing unit 20 that is supported by the body 10 and that is configured to capture a distance image ahead of the user, a line-of-sight direction detection unit 22 that is supported by the body 10 and that is configured to detect a line-of-sight direction of the user, a control unit 40 that is configured to obtain distance information on a target portion in the line-of-sight direction in the distance image, and distance information output units 30, 32, 34 that are configured to output the distance information through sound or tactile sensation.

Automated indexing and extraction of multiple information fields in digital records

Systems and Methods are disclosed herein for automatically indexing multiple informational fields in digital data records, the method comprising: identifying, based on rules defining target information fields, for each target field of the target information fields, at least one page in a digital data record comprising content related to the target field; extracting, for each target field, from the identified at least one page, at least one portion of text comprising the content; feeding, for each target field, a pre-processed version of the at least one portion of text into a machine learning (ML) model, wherein the ML model is trained on the target field; determining, for each target field, via the ML model trained on the target field, at least one candidate text comprising the content; and extracting, for each target field, the at least one candidate text.

AN ELECTRONIC INPUT WRITING DEVICE FOR DIGITAL CREATION AND A METHOD FOR OPERATING THE SAME

An electronic writing device is disclosed. The device includes an inertial measurement unit to measure motion of a finger of a user, activates the electronic writing device to perform pincer grip analysis of the user. An image acquisition unit captures one or more images of an object present. A colour sensor to recognize one or more colours of the one or more images of the object captured. A light sensor illuminates a colour of light corresponding to the one or more colours of the one or more images of the object. An image processing subsystem creates a multi-dimensional representation of the one or more images of the object, identifies one or more parameters associated with the object from the multi-dimensional representation created, recognizes a plurality of characters from the multi-dimensional representation of the one or more images of the object, analyzes a language of the plurality of characters recognized from the multi-dimensional representation.

INTERACTIVE VOICE RESPONSE SYSTEMS HAVING IMAGE ANALYSIS

An interactive voice response system is provided that includes an interactive voice recognition module, an image collection module, and a data extraction module. The image collection module communicates with the voice recognition module and the user device. The extraction module communicates with the image collection module. The voice recognition module collects speech data from a user of the user device and provides an indication to the image collection module when the speech data includes complex data. The image collection module, in response to the indication, communicates with the user device in a text message. The text message includes a link that, when activated, opens a camera on the user device. The image collection module, in response to receiving an image having the complex data from the camera, communicates the image to the extraction module, which extracts the complex data from the image as textual data.

Computer Vision Systems and Methods for Information Extraction from Floorplan Images

Computer vision systems and methods for information extraction from floorplan images are provided. The system generates a multi-attributed graph representing an architectural floorplan image having nodes representing rooms of the floorplan image and connecting edges therebetween representing connectivity between the rooms. Each node of the multi-attributed graph can have multiple attributes including a type of the room, a room size, and the floor number on which room lies. Each edge can have attributes to denote a type of connectivity, such as door-based, wall-based, wall-with-window-based, and vertical connectivity where one room is located beneath another room on a separate floor of the floorplan image.

VISION-BASED SYSTEM AND METHOD FOR PROVIDING INVENTORY DATA COLLECTION AND MANAGEMENT

A system and method determines from data collected by one or more data collection elements of a computing device a plurality of discrete product storage locations within a product storage system. Each of the plurality of plurality of discrete product storage locations is caused to be associated with at least one cell of a grid comprised of a plurality of cells. A graphical user interface is displayed in a display of the computing device, the graphical user interface including the grid overlayed upon an image of the product storage system. A user may then interact with the graphical user interface to select a one or more of the plurality of cells of the grid and cause product related information captured via use of the one more data collection elements of the computing device to be linked in a memory storage associated with the computing device to the one of the plurality of discrete product storage locations that was associated with the selected at least one cell of the grid.

METHOD AND SYSTEM FOR PROVIDING LANGUAGE LEARNING SERVICES

The present invention relates to a method and system for providing language learning services. The method of providing language learning services, according to the present invention, the method may include: activating, in response to receiving an input for acquiring a learning target image through a user terminal, a camera of the user terminal; specifying at least a portion of an image taken by the camera as the learning target image; receiving language learning information for the learning target image from a server; providing the language learning information to the user terminal; and storing, based on a request for storing of the language learning information, the language learning information in association with the learning target image, such that the learning target image is used in conjunction with learning of the language learning information.

Enabling Electronic Loan Documents

The system prepares PDF documents to be digitally populated or signed. The method may comprise converting a document into an image; detecting words on the document; searching the words for keywords; searching for an object on the document; determining an object field based on the keywords and the object; creating a tag with metadata about the object field; and associating the tag with the object field. The method may also comprise determining, by a processor, metadata about a document; creating, by the processor, a hash from the metadata; storing, by the processor, an association of the hash, the metadata and the document in a knowledge database; creating, by the processor, a new hash for a new document; comparing, by the processor, the hash with the new hash; and determining, by the processor, that the new document has similar characteristics as the document based on the comparing.

Cross-Modal Weak Supervision For Media Classification

Methods, systems, and storage media for classifying content across media formats based on weak supervision and cross-modal training are disclosed. The system can maintain a first feature classifier and a second feature classifier that classifies features of content having a first and second media format, respectively. The system can extract a feature space from a content item using the first feature classifier and the second feature classifier. The system can apply a set of content rules to the feature space to determine content metrics. The system can correlate a set of known labelled data to the feature space to construct determinative training data. The system can train a discrimination model using the content item and the determinative training data. The system can classify content using the discrimination model to assign a content policy to the second content item.

DISPLAY APPARATUS, DISPLAY METHOD, AND DISPLAY SYSTEM

A display apparatus includes circuitry to receive an input of hand drafted data, display, on a display, an object corresponding to the hand drafted data and an external image that is externally input, perform character recognition on the hand drafted data to convert the hand drafted data into text data, and display, on the display, a search result obtained using at least a part of the external image and at least a part of the text data.

Section-linked document classifiers

Disclosed herein are system, method, and computer program product embodiments for rapid identification and access to relevant regulatory documents. A data model relating regulatory mandates and requirements to citations appearing within an enforcement document is used to rapidly access specific citations within an enforcement document. In the case of image-based enforcement documents, the originality of these documents is preserved while allowing a user to see where the relevant citations appear in the document images.

ELECTRONIC HEALTH RECORDS ANALYSIS USING ROBOTIC PROCESS AUTOMATION

Provided is a method, system, and computer program product for analyzing an electronic health record (EHR) using robotic process automation (RPA). A processor may analyze an EHR associated with a user. The processor may identify, based on analyzing the EHR, one or more health parameters that are outside of a threshold range. The processor may determine a set of recommended actions that may be performed to cause the health parameter to fall within the threshold range. The processor may analyze activity data associated with the user. The processor may identify, based on the activity data, a set of known activities performed by the user. The processor may correlate the recommended actions with the known activities to identify a subset of personalized actions that are specific to the user. The processor may send the subset of personalized actions to the user.

MACHINE LEARNING MODELS FOR AUTOMATED DIAGNOSIS OF DISEASE DATABASE ENTITIES

A method of automated diagnosis of disease database entities includes receiving a case processing request via an input application programming interface (API), extracting image data from the case processing request including at least one medical scan image of the patient, selecting at least a portion of the medical scan image(s) according to specified selection criteria, normalizing the selected at least a portion of the medical scan image(s), supplying the selected at least a portion of the medical scan image(s) to a machine learning model to generate a target medical condition prediction output, wherein the target medical condition prediction output is indicative of a likelihood that a patient will experience a future disease diagnosis event corresponding to the target medical condition, and automatically transmitting the target medical condition prediction output as an electronic transmission via an output API to a provider system associated with the patient.

Structuring unstructured data via optical character recognition and analysis

The present disclosure describes devices and methods of providing a technology environment for analyzing unstructured data to generate structured data. A set of electronic documents, each electronic document associated with a type of product, may be accessed. A data instance for each of the documents may be generated. The data instance may include a plurality of data fields that are based on the type of product. The electronic documents may be analyzed to identify values for each of the plurality of data fields. Analyzing the electronic documents may comprise applying a respective character recognition algorithm to respective electronic documents, and assigning a confidence factor to each of the values. The data instances comprising the values for each of the plurality of data fields may be stored in a second database.

SYSTEMS AND METHODS FOR QUESTION-ANSWERING USING A MULTI-MODAL END TO END LEARNING SYSTEM

A multi-modal end to end learning system configured to answer questions about clinical documents like patient notes, medical reports, and lab results. Documents are polled from an electronic medical record system, converted to text, and scrubbed for protected health information before processing. Sanitized text data is then fed as context to a language model that has been fine-tuned for question-answering (QA). The other input to the model is a prompt or a question that is either provided on-the-fly by a clinician as part of a search or pre-determined for specific needs. In return, the model outputs an answer highlighting part of the text/image where it found the answer and a confidence score quantifying the likelihood of the answer being correct. A clinician can optionally correct the answer if needed. This feedback by the clinician is fed back to a fine-tuner module and used to improve the model over time.

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING SYSTEM, CONTROL METHOD OF THE SAME, AND STORAGE MEDIUM

An image processing apparatus for setting a property of a document file by using a result of a character recognition process performed on a scanned image of a document is provided and includes an obtaining unit and an a setting unit. The obtaining unit obtains a character string by performing the character recognition process on a scanned image relating to a document file to be generated in this operation. The setting unit automatically sets the character string obtained by the obtaining unit as a character string to be used in a property of the document file to be generated in this operation if the character string obtained by the obtaining unit is a character string obtained in the character recognition process performed on a scanned image relating to a document file generated in the past and approved by a user a certain number of times or more.

Rapid language detection for characters in images of documents

A computer-implemented method, according to one embodiment, includes: receiving an image having characters that correspond to a language, and using a text recognition algorithm to determine a first language believed to correspond to the characters. A first confidence level associated with the first language is also computed, and a determination is made as to whether the first confidence level associated with the first language is outside a predetermined range. In response to determining that the first confidence level associated with the first language is not outside the predetermined range, the first language is output as the given language. The text recognition algorithm is trained using a simple shallow neural network and a generated mixed language corpus. The generated mixed language corpus is formed by: randomly sampling libraries having vocabulary and/or characters therein, and combining the randomly sampled vocabulary and/or characters to form the generated mixed language corpus.

System and method for generating accessible user experience design guidance materials

A system and method for generating accessible user experience (UX) design guidance materials for software products uses page elements that are optically extracted from an input UX prototype page image and automatically classified into predefined element types to find accessibility rules for at least some of the extracted page elements. At least one accessible UX design guidance material is generated for the input UX prototype page image that indicates the extracted page elements and the accessibility rules corresponding to at least some of the extracted page elements.

SYSTEMS AND METHODS FOR CLASSIFYING DOCUMENTS

A system may iteratively scan a portion of a document, extract first data from the portion of the document, and determine, using a trained model, whether the first data corresponds to one or more document types based on one or more confidence thresholds. The system may repeat this process, increasing the portion of the document scanned by a predetermined amount each iteration, until the first data corresponds to the one or more document types based on the one or more confidence thresholds. Responsive to determining the first data corresponds to the one or more document types based on the one or more confidence thresholds, the system may cause a graphical user interface (GUI) of a user device to display a notification indicating a document type match.

CHAT ATTACHMENT SCREENING

Certain aspects of the present disclosure provide techniques and systems for screening chat attachments. A chat attachment screening system monitors a chat window of a first computing device associated with a first user during an interaction session between the first user and a second user. An upload of an attachment is detected based on the monitoring. Access to the attachment from a second computing device associated with the second user is blocked, in response to detecting the upload. Content from the attachment is identified and extracted. A type of the attachment is determined based on the content. A determination is made as to whether the second user is authorized to access the type of the attachment. An indication of the determination is presented on at least one of the first computing device or the second computing device during the interaction session.

SYSTEM AND METHOD FOR IMPLEMENTING A MULTIMODAL ASSISTANT USING LARGE LANGUAGE MODELS

An embodiment of the present invention is directed to a multimodal assistant for mechanics and technicians in military warehouses using large language models. An exemplary system provides a conversational assistant to mechanics and technicians working in challenging environments, such as shop or warehouse floors with heavy industrial equipment and componentry. The innovative system may utilize multimodal large language models as well as image segmentation techniques to efficiently retrieve relevant information from asset reference materials, documentation and other sources of instructional information. The system may also use multimodal large language models to extract information from the retrieved documents and/or other data sources to provide guidance on performing discrete tasks related to the asset, such as routine maintenance, part replacement, services and/or other related actions.

Cross-medium copying of selections of content shared during a video conference

Selections of content shared from a remote device during a video conference are copied to a destination of a computing device connected to the video conference live or at which a recording of the video conference is viewed. The content shared from the remote device during the video conference is output at a display of the computing device. A portion of the content is selected according to an instruction received from a user of the computing device while output at the display of the computing device to copy to a destination associated with software running at the computing device. The portion of the content is identified using a machine vision process performed against the content while output at the display of the computing device. The portion of the content is then copied to the destination.

SYSTEMS AND METHODS FOR PATTERN-BASED MULTI-STAGE DETERMINISTIC DATA CLASSIFICATION

Systems and methods for pattern-based multi-stage deterministic data classification that may reduce processing and memory overhead while providing more accurate data classifications.

PICTURE DISPLAY METHOD AND APPARATUS, ELECTRONIC DEVICE, AND MEDIUM

A picture display method, an apparatus, and a medium are provided. The picture display method includes: obtaining a first picture, and the first picture including a first region and a second region arranged in a first direction; and displaying a second picture when a first size of the first picture in the first direction satisfies a predetermined condition, and the second picture including the first region and the second region arranged in a second direction.

Apparatuses and methods for querying and transcribing video resumes

Aspects relate to apparatuses and methods for generating queries and transcribing video resumes. An exemplary apparatus includes at least a processor and a memory communicatively connected to the processor, the memory containing instructions configuring the processor to receive, from a posting generator, a plurality of posting inputs from a plurality of postings, receive a video resume from a user, generate a plurality of queries as a function of the video resume based on a plurality of posting categories, transcribe, as a function of the plurality of queries, a plurality of user inputs from the video resume, wherein the plurality of user inputs is related to attributes of a user, and classify the plurality of user inputs to the plurality of posting inputs to match the user to the plurality of postings.

SYSTEM AND METHOD FOR INTERNAL ETCHING SURFACES OF TRANSPARENT MATERIALS WITH INFORMATION PERTAINING TO A BLOCKCHAIN

In one embodiment, a system including a tangible token comprising a single integrated transparent gemstone produced by fusing together a first transparent gemstone and a second transparent gemstone, a first internal side of the first transparent gemstone is etched with information pertaining to a blockchain, and the information comprises at least a private key, a public key, and an address, the first internal side of the first transparent gemstone is aligned with a second internal side of the second transparent gemstone, and the aligning encapsulates the information within a perimeter of the second internal side such that the information does not extend beyond the perimeter. The system includes a computing device that executes instructions to: read the information, validate, via a network and the address, the public key and private key are associated with the blockchain, and present an indication of whether or not the information is validated.

METHODS AND SYSTEMS FOR DYNAMICALLY ESTABLISHING A VIDEO CONFERENCE CONNECTION BETWEEN A COMPUTING DEVICE OF A FIRST USER AND A COMPUTING DEVICE OF A SECOND USER DURING A VIEWING OF A VIDEO BY THE FIRST USER

A method for dynamically establishing a video conference connection between a computing device of a user and a computing device of a second user during a viewing of a video by the user includes receiving, by a first computing device, from a second computing device, a first user input responsive to a first segment of a video displayed to a first user of the second computing device. A recommendation engine analyzes the first user input and selects a second user of a third computing device. The first computing device establishes a video conferencing connection between the second and third computing devices. The first computing device receives an indication of a termination of the video conferencing connection and third user input. The recommendation engine selects a second segment of the video for display, responsive to analysis of the third user input, and directs the display of the selected second segment.

Устройство для автоматизированного распознавания поведения с целью выявления агрессии

Полезная модель относится к области дистанционного анализа и классификации движений человека и может быть использована для автоматизированного поведения с целью выявления агрессии. Технический результат заключается в расширении потенциальных возможностей дистанционного анализа и повышении точности классификации движений человека на основе видеоанализа за счет использования дополнительного биорадиолокационного канала информации с целью выявления агрессивного поведения. Устройство, содержащее видеокамеру, блок нахождения на изображении человека и выделения узловых точек его силуэта, блок извлечения признаков из координат узловых точек, извлеченных из видеопоследовательности, блок первичной классификации поведения по данным видеоканала, биорадиолокатор, блок первичной фильтрации биорадиолокационных сигналов, блок нормализации биорадиолокационного сигнала, блок извлечения признаков биорадиолокационного сигнала, блок нормализации признаков биорадиолокационного сигнала, блок первичной классификации поведения по данным биорадиолокационного канала, блок вторичной классификации, блок сопряжения с устройством вывода. 1 ил. РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 196 355 U1 (51) МПК G06T 7/20 (2006.01) H04N 19/43 (2014.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ПОЛЕЗНОЙ МОДЕЛИ К ПАТЕНТУ (52) СПК G06K 9/00 (2019.08); G06K 9/66 (2019.08) (21)(22) Заявка: 2019120242, 26.06.2019 (24) Дата начала отсчета срока действия патента: (73) Патентообладатель(и): Анищенко Леся Николаевна (RU) Дата регистрации: 26.02.2020 Приоритет(ы): (22) Дата подачи заявки: 26.06.2019 (45) Опубликовано: 26.02.2020 Бюл. № 6 1 9 6 3 5 5 R U (54) Устройство для автоматизированного распознавания поведения с целью выявления агрессии (57) Реферат: Полезная модель относится к области выделения узловых точек его силуэта, блок дистанционного анализа и классификации извлечения признаков из координат узловых движений человека и может быть использована точек, извлеченных из ...

Method for a Pattern Discovery and Recognition

A method is for a pattern discovery and recognition, wherein a first sequence comprising first sequence symbols relating to a concept and a tag associated to the first sequence are received, transition probability matrices are obtained from transition frequency matrices representing the frequency data of the occurrences of the transitions between the first sequence symbols at different distances in the first sequence, and the transition probability matrices for each tag and each distance are learnt for obtaining an activation function determining the concept occurring in a second sequence. A computer program product and an apparatus are for executing the pattern discovery and recognition method.

Real-Time Face Tracking in a Digital Image Acquisition Device

A database includes an identifier and associated parameters for each of a number of faces to be recognized. A new acquired image from an image stream is received potentially including one or more face regions. Face detection is applied to at least a portion of the acquired image to provide a set of candidate face regions each having a given size and a respective location. Using the database, face recognition is selectively applied to at least one of the candidate face regions to provide an identifier for a face recognized in a candidate face region. A portion of the image is stored including the recognized face in association with at least one image of the image stream.

Real-Time Face Tracking in a Digital Image Acquisition Device

An image processing apparatus for tracking faces in an image stream iteratively receives an acquired image from the image stream including one or more face regions. The acquired image is sub-sampled at a specified resolution to provide a sub-sampled image. An integral image is then calculated for a least a portion of the sub-sampled image. Fixed size face detection is applied to at least a portion of the integral image to provide a set of candidate face regions. Responsive to the set of candidate face regions produced and any previously detected candidate face regions, the resolution is adjusted for sub-sampling a subsequent acquired image.

Image processing apparatus, image processing method and computer-readable medium

An image processing apparatus includes a cutout position extraction unit, a character candidate extraction unit, a graph generation unit, a link value generation unit, a path selection unit and an output unit. The cutout position extraction unit extracts a cutout position. The character candidate extraction unit recognizes each character for each character image divided by the cutout position and extracts a plurality of character candidates for each recognized character. The graph generation unit sets each of the plurality of extracted character candidates as a node and generates a graph by establishing links between the nodes of adjacent character images. The link value generation unit generates a link value based on a value of character-string-hood representing a relationship between character candidates. The path selection unit selects a path in the generated graph based on the link value. The output unit outputs a character candidate string in the selected path.

BEGIN ANCHOR ANNOTATION IN DFAs

Disclosed is a method and system of matching a string of symbols to a ruleset. The ruleset comprise a set of rules. The method includes ignoring begin anchor requirements when constructing a DFA from all the rules of the ruleset, annotating the accepting states of the DFA with the begin anchor information, executing the DFA, and checking begin anchor annotations to determine if begin anchor requirement are satisfied if an accepting state is reached. Embodiments also include rulesets with begin anchors on matches, rulesets with early exit information on non-accepting states, and rulesets with accept begin anchors in accepting states.

Automated search for detecting patterns and sequences in data using a spatial and temporal memory system

A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.

Image processing learning device, image processing learning method, and image processing learning program

Disclosed is a technology with which face direction estimation processing and face detection processing can be learned simultaneously and with high precision without incurring significant costs. The image processing learning device comprises: a face direction identification unit that identifies whether a face direction is already known; a position conversion unit that converts information regarding the face direction to a position on a manifold, when already known; a position estimation unit that estimates the position on the manifold, when unknown; a face identification unit that identifies whether an object is already known to be a face/not a face; a first update quantity calculation unit that calculates the update quantity according to whether the object is a face/not a face from the distance between the position on the manifold and the position in space, when already known; a second update quantity calculation unit that calculates the update quantity so as to be closer when the distance between the position on the manifold and the position in space is close, and further when far, when unknown; and a parameter update unit that updates parameters. The image processing learning device comprises: a face direction identification unit that identifies whether a face direction is already known; a position conversion unit that converts information regarding the face direction to a position on a manifold, when already known; a position estimation unit that estimates the position on the manifold, when unknown; a face identification unit that identifies whether an object is already known to be a face/not a face; a first update quantity calculation unit that calculates the update quantity according to whether the object is a face/not a face from the distance between the position on the manifold and the position in space, when already known; a second update quantity calculation unit that calculates the update quantity so as to be closer when the distance between the position ...

Information processing method, information processing apparatus, and recording medium

The robustness of discriminating results at each stage is improved in discrimination processing in which a plurality of stages of discriminators are used to identify an object. An information processing apparatus in which a plurality of stages of the discriminators are used to identify a class of an object, comprises a candidate class output unit that acquires as a candidate class a class discriminated at a first stage of the discriminators, and an extended class setting unit that sets in a second stage of the discriminators, a class of a second stage of the discriminators, which is defined as an extended partial space of a partial space defined by a candidate class in a discriminating space used in discriminating the candidate class by the first stage of the discriminators, as a class to be discriminated at this second stage of the discriminators.

Image segmentation based on approximation of segmentation similarity

A system and a method for image segmentation use segmentation maps of one or more similar images as a basis for the segmentation. The method includes generating an image signature for an input image to be segmented and identifying at least one similar image from a set of images, based on the image signature of the input image and image signatures of images in the set of images. The similarity may be computed after first projecting the image signatures into a feature space where similarity is more likely to agree with segmentation map similarity. The input image is segmented, based on the segmentation map of one or more of the at least one identified similar images.

Nondestructive method to predict isostatic strength in ceramic substrates

A method of examining a cellular structure includes the steps of providing an inspecting device, a neural network and a target cellular structure that includes a plurality of target cells extending therethrough and further includes a target face exposing an arrangement of the target cells; inspecting the arrangement of cells on the face of the target cellular structure using the inspecting device; representing the arrangement of cells with numerically defined target cell parameters; inputting the target cell parameters into the neural network; and generating an output from the neural network based on the target cell parameters, the output being indicative of a strength of the target cellular structure.

Method and apparatus for tracking object in image data, and storage medium storing the same

Disclosed is a system for tracking an object in an image. A method for tracking an object in an image according to an exemplary embodiment of the present invention includes generating an object model represented by multiple patch histograms of an object that is divided into N partial patch regions and histograms are built from each patch region, forming an object model; estimating the probability of each image pixel being an object pixel; and determining the most promising location of an object in the image by using the estimated object probability values. According to the exemplary embodiment of the present invention, it is possible to more improve separability from a background than a case in which a single histogram mode is used, to increase tracking performance, and to more accurately search the object region than a mean-shift method of the related art.

Methods, systems, and data structures for performing searches on three dimensional objects

Techniques are provided for searching on three dimensional (3D) objects across large, distributed repositories of 3D models. 3D shapes are created for input to a search system; optionally user-defined similarity criterion is used, and search results are interactively navigated and feedback received for modifying the accuracy of the search results. Search input can also be given by picking 3D models from a cluster map or by providing the orthographic views for the 3D model. Feedback can be given by a searcher as to which models are similar and which are not. Various techniques adjust the search results according to the feedback given by the searcher and present the new search results to the searcher.

Recording media processing device, control method of a recording media processing device, and storage medium

The recognition rate is improved and recognition errors are suppressed when recognizing magnetic ink characters. A character recognition unit 80 calculates the difference between the reference waveform data of each character in a character set and the character waveform data of a read magnetic ink character 101 , and defines the characters with the smallest differences to the read character as first and second candidate characters. If scaling the reference waveforms of the first and second candidate characters creates waveforms that are similar with a smaller difference therebetween than before scaling, and the ratio between the difference B between the waveform of the second candidate and the read character, and the difference A between the waveform of the first candidate and the read character, is greater than or equal to a specific value, the character recognition unit scales and adjusts the reference waveforms to recognize the magnetic ink character 101.

Small Vein Image Recognition and Authorization Using Constrained Geometrical Matching and Weighted Voting Under Generic Tree Model

An automated registration and authentication system combines a generative and discriminative approach to improve the matching of a query object to a database of registered objects. The discriminative approach uses a voting mechanism to identify a most likely match, and the generative approach uses ASIFT transforms to determine a best geometric match. The two results are combined using a technique base on Bayesian inference theory.

Redundant aspect ratio decoding of devanagari characters

An electronic device and method receive a block sliced from a rectangular portion of an image of a scene of real world captured by a camera and use a property of the block to operate one of multiple optical character recognition (OCR) decoders. In an illustrative aspect, a first OCR decoder is configured to recognize characters whose property satisfies the test based on a first limit, the first limit being obtained by reducing a predetermined limit by an overlap amount. In this illustrative aspect, a second OCR decoder is configured to recognize characters whose property does not satisfy the test based on a second limit, the second limit being obtained by increasing the predetermined limit by the overlap amount. When the property of the block satisfies the test, the first OCR decoder is operated and alternatively the second OCR decoder is operated, resulting in candidates for a character being identified.

Method and device for creating a machine learning system

A method for creating a machine learning system which is designed for segmentation and object detection in images. The method includes: providing a directed graph; selecting a path through the graph, at least one additional node being selected from this subset, a path through the graph from the input node along the edges via the additional node up to the output node being selected; creating a machine learning system as a function of the selected path; and training the machine learning system created.

Method and appartaus for data efficient semantic segmentation

A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

Determining an item that has confirmed characteristics

In various example embodiments, a system and method for determining an item that has confirmed characteristics are described herein. An image that depicts an object is received from a client device. Structured data that corresponds to characteristics of one or more items are retrieved. A set of characteristics is determined, the set of characteristics being predicted to match with the object. An interface that includes a request for confirmation of the set of characteristics is generated. The interface is displayed on the client device. Confirmation that at least one characteristic from the set of characteristics matches with the object depicted in the image is received from the client device.

Image processing apparatus, training apparatus, image processing method, training method, and storage medium

There is provided with an image processing apparatus, for example, for image recognition. An extraction unit extracts a feature amount from a target image. An estimation unit estimates distribution of regions having attributes different from each other in the target image based on the feature amount.

Alignment of video and textual sequences for metadata analysis

Systems, methods and computer program products related to aligning heterogeneous sequential data. A first sequential data stream and a second sequential data stream are received. An action related to aligning the first sequential data stream and the second sequential data stream is determined using an alignment neural network. The alignment neural network includes a fully connected layer that receives as input: data from the first sequential data stream, data from the second sequential data stream, and data relating to a previously determined action by the alignment neural network related to aligning the first sequential data stream and the second sequential data stream.

Systems and methods to improve data clustering using a meta-clustering model

Systems and methods for clustering data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving data from a client device and generating preliminary clustered data based on the received data, using a plurality of embedding network layers. The operations may include generating a data map based on the preliminary clustered data using a meta-clustering model. The operations may include determining a number of clusters based on the data map using the meta-clustering model and generating final clustered data based on the number of clusters using the meta-clustering model. The operations may include and transmitting the final clustered data to the client device.

Systems and methods for hyperparameter tuning

A model optimizer is disclosed for managing training of models with automatic hyperparameter tuning. The model optimizer can perform a process including multiple steps. The steps can include receiving a model generation request, retrieving from a model storage a stored model and a stored hyperparameter value for the stored model, and provisioning computing resources with the stored model according to the stored hyperparameter value to generate a first trained model. The steps can further include provisioning the computing resources with the stored model according to a new hyperparameter value to generate a second trained model, determining a satisfaction of a termination condition, storing the second trained model and the new hyperparameter value in the model storage, and providing the second trained model in response to the model generation request.

Systems and methods to identify neural network brittleness based on sample data and seed generation

Systems and methods for determining neural network brittleness are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a modeling request comprising a preliminary model and a dataset. The operations may include determining a preliminary brittleness score of the preliminary model. The operations may include identifying a reference model and determining a reference brittleness score of the reference model. The operations may include comparing the preliminary brittleness score to the reference brittleness score and generating a preferred model based on the comparison. The operations may include providing the preferred model.

Protecting Enterprise Computing Resources by Implementing an Optical Air Gap System

Aspects of the disclosure relate to protecting enterprise computing resources by implementing an optical air gap system. A computing platform may receive, from an external communications server, a message. The computing platform then may generate an image representation of the message received from the external communications server. Subsequently, the computing platform may execute an optical character recognition (OCR) process on the image representation of the message, which may produce a recreated message. Then, the computing platform may validate contents of the recreated message. Based on validating the contents of the recreated message, the computing platform may send, to an enterprise communications server, the recreated message, and sending the recreated message to the enterprise communications server may cause the enterprise communications server to deliver the recreated message to at least one enterprise user computing device.

Document information extraction for computer manipulation

Systems and apparatuses are disclosed for extracting information from document images. An example method includes segmenting a document image into multiple segments and determining formatting information for each segment. Determining formatting information for a segment includes determining one or more features of the segment and comparing the one or more features of the segment to one or more clusters of features associated with different document types. The formatting information for the segment is based on the comparison. The method also includes, for each segment, storing the formatting information in a data structure associated with the segment. The method further includes, for each segment including text to be identified during information extraction, applying OCR to the segment to generate machine-encoded text and storing the machine-encoded text in the associated data structure.

Noise-enhanced convolutional neural networks

A learning computer system may include a data processing system and a hardware processor and may estimate parameters and states of a stochastic or uncertain system. The system may receive data from a user or other source; process the received data through layers of processing units, thereby generating processed data; apply masks or filters to the processed data using convolutional processing; process the masked or filtered data to produce one or more intermediate and output signals; compare the output signals with reference signals to generate error signals; send and process the error signals back through the layers of processing units; generate random, chaotic, fuzzy, or other numerical perturbations of the received data, the processed data, or the output signals; estimate the parameters and states of the stochastic or uncertain system using the received data, the numerical perturbations, and previous parameters and states of the stochastic or uncertain system; determine whether the generated numerical perturbations satisfy a condition; and, if the numerical perturbations satisfy the condition, inject the numerical perturbations into the estimated parameters or states, the received data, the processed data, the masked or filtered data, or the processing units.

Systems and methods to optimize performance of a machine vision system

Methods and systems for optimizing performance of a machine vision system are disclosed herein. An example method includes obtaining one or more first and second images of a target object, where each of the one or more first and second images include a pass indication and a fail indication, respectively. The example method further includes conducting, by a feasibility setup tool, a feasibility setup analysis by (i) performing machine vision techniques on each of the one or more first and second images and (ii) generating a respective updated result indication for each of the one or more first and second images. The example method further includes comparing the respective updated result indication to the respective pass indications and fail indications for the one or more first and second images, respectively; and based on the comparing, generating one or more suggestions to optimize the performance of the machine vision system.

Lens distortion correction using a neurosynaptic circuit

One or more embodiments provide a neurosynaptic circuit that includes multiple neurosynaptic core circuits that: perform image sharpening by converting a source image to a sharpened destination image by: taking as input a sequence of image frames of a video with one or more channels per frame, and representing the intensity of each pixel of each channel of each frame as neural spikes; processing the source image to obtain the sharpened destination image for a particular frame and channel that enhances certain high frequency components of the source image; and processing neural spike representations of the destination image for outputting a spike representation of the sharpened destination image.

Systems and methods for extracting data from an image

Embodiments of the present disclosure pertain to systems and method for extracting data from an image. In one embodiment, a method of extracting data from an image comprises receiving, from an optical character recognition (OCR) system, OCR text in response to sending an image to the OCR system. The OCR text comprises a plurality of lines of text. Each line of text is classified as either a line item or not a line item using a machine learning algorithm, and a plurality of data fields are extracted from each line of text classified as a line item.

Method and system for analyzing biological specimens by spectral imaging

The methods, devices, and systems may allow a practitioner to obtain information regarding a biological sample, including analytical data, a medical diagnosis, and/or a prognosis or predictive analysis. The method, devices, and systems may provide a grade or level of development for identified diseases. In addition, the methods, devices and systems may generate a confidence value for the predictive classifications generated, which may, for example be generated in a format to show such confidence value or other feature in a graphical representation (e.g., a color code). Further, the methods, devices and system may aid in the identification and discovery of new classes and tissue sub-types.

Text detection, caret tracking, and active element detection

Detection of typed and/or pasted text, caret tracking, and active element detection for a computing system are disclosed. The location on the screen associated with a computing system where the user has been typing or pasting text, potentially including hot keys or other keys that do not cause visible characters to appear, can be identified and the physical position on the screen where typing or pasting occurred can be provided based on the current resolution of where one or more characters appeared, where the cursor was blinking, or both. This can be done by identifying locations on the screen where changes occurred and performing text recognition and/or caret detection on these locations. The physical position of the typing or pasting activity allows determination of an active or focused element in an application displayed on the screen.

Recognition method and recognition system for unambiguously recognizing an object

The presented invention relates to a computer-implemented recognition method ( 100 ) for unambiguously recognizing an object. The recognition method ( 100 ) comprises a first determining step ( 101 ) for determining, by means of a first optical sensor ( 201 ) at a first point in time, reference information by capturing a number of symbols applied to a reference object, a training step ( 103 ) for training a machine learner on the basis of the reference information and a provided ground truth which assigns respective reference information to a first class or a further class, a second determining step ( 105 ) for determining, by means of a second optical sensor ( 205 ) at a second point in time, sample information by capturing a number of symbols applied to a sample object, an assigning step ( 107 ) for the assigning of the sample information to the first class or the further class by the machine learner, and an outputting step ( 109 ) for outputting a validation signal in case the machine learner assigns the sample information to the first class. Furthermore, the presented invention relates to a recognition system ( 200 ).

Systems and methods to process electronic images to provide image-based cell group targeting

Systems and methods are disclosed for grouping cells in a slide image that share a similar target, comprising receiving a digital pathology image corresponding to a tissue specimen, applying a trained machine learning system to the digital pathology image, the trained machine learning system being trained to predict at least one target difference across the tissue specimen, and determining, using the trained machine learning system, one or more predicted clusters, each of the predicted clusters corresponding to a subportion of the tissue specimen associated with a target.

Methods and systems for characterizing tissue of a subject utilizing a machine learning

Methods and systems for characterizing tissue of a subject include acquiring and receiving data for a plurality of time series of fluorescence images, identifying one or more attributes of the data relevant to a clinical characterization of the tissue, and categorizing the data into clusters based on the attributes such that the data in the same cluster are more similar to each other than the data in different clusters, wherein the clusters characterize the tissue. The methods and systems further include receiving data for a subject time series of fluorescence images, associating a respective cluster with each of a plurality of subregions in the subject time series of fluorescence images, and generating a subject spatial map based on the clusters for the plurality of subregions in the subject time series of fluorescence images. The generated spatial maps may then be used as input for tissue diagnostics using supervised machine learning.

Multi-word phrase based analysis of electronic documents

A document processing system is configured to identify, for each accessed electronic document in a first set of multiple electronic documents, a set of identified multi-word phrases determined to be in ordered text information in the accessed electronic document, each multi-word phrase of the set of identified multi-word phrases including adjacent words in the ordered text information; and determine, for each accessed electronic document in the first set of multiple electronic documents, a selected document type from the first set of document types based at least on an analysis of the set of identified multi-word phrases with respect to multi-word-phrase characteristics identified by a first definition and associated with each document type in a first set of document types associated with a first document-set type.

Optical character recognition of documents having non-coplanar regions

Systems and methods for performing OCR of an image depicting text symbols and imaging a document having a plurality of planar regions are disclosed. An example method comprises: receiving a first image of a document having a plurality of planar regions and one or more second images of the document; identifying a plurality of coordinate transformations corresponding to each of the planar regions of the first image of the document; identifying, using the plurality of coordinate transformations, a cluster of symbol sequences of the text in the first image and in the one or more second images; and producing a resulting OCR text comprising a median symbol sequence for the cluster of symbol sequences.

Optical neural network unit and optical neural network configuration

An artificial neuron unit and neural network for processing of input light are described. The artificial neuron unit comprises a modal mixing unit, such as multimode optical fiber, configured for receiving input light and applying selected mixing to light components of two or more modes within the input light and for providing exit light, and a filtering unit configured for applying preselected filter onto said exit light for selecting one or more modes of the exit light thereby providing output light of the artificial neuron unit.

Applying live camera colors to a digital design

The present disclosure is directed toward systems and methods for extracting colors from a live camera feed and applying the extracted colors to a user's input digital design. For example, in response to the user targeting the camera of a client-computing device at a fixed position for a threshold amount of time, one or more embodiments described herein extracts a palette of dominant colors from the live camera feed and maps the palette of dominant colors onto one or more colors of the user's input digital design in real time.

Modifying a graphic design to match the style of an input design

The present disclosure is directed toward systems and methods for retargeting a user's input digital design based on a selected template digital design. For example, in response to the user's selection of a template digital design, one or more embodiments described herein change various design features of the user's input digital design to match corresponding design features in the selected template digital design. One or more embodiments described herein also provide template digital designs to the user for use in retargeting after a two-step selection process that ensures the provided template digital designs are compatible with the user's input digital design.

Face identification using artificial neural network

Automated facial recognition is performed by operation of a convolutional neural network including groups of layers in which the first, second, and third groups include a convolution layer, a max-pooling layer, and a parametric rectified linear unit activation function layer. A fourth group of layers includes a convolution layer and a parametric rectified linear unit activation function layer.

Steering Seismic Texture Analysis Algorithms Using Expert Input

A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.

Emoji Understanding in Online Experiences

Understanding emojis in the context of online experiences is described. In at least some embodiments, text input is received and a vector representation of the text input is computed. Based on the vector representation, one or more emojis that correspond to the vector representation of the text input are ascertained and a response is formulated that includes at least one of the one or more emojis. In other embodiments, input from a client machine is received. The input includes at least one emoji. A computed vector representation of the emoji is used to look for vector representations of words or phrases that are close to the computed vector representation of the emoji. At least one of the words or phrases is selected and at least one task is performed using the selected word(s) or phrase(s).

Font Recognition using Text Localization

Font recognition and similarity determination techniques and systems are described. In a first example, localization techniques are described to train a model using machine learning (e.g., a convolutional neural network) using training images. The model is then used to localize text in a subsequently received image, and may do so automatically and without user intervention, e.g., without specifying any of the edges of a bounding box. In a second example, a deep neural network is directly learned as an embedding function of a model that is usable to determine font similarity. In a third example, techniques are described that leverage attributes described in metadata associated with fonts as part of font recognition and similarity determinations.

System and method for textual analysis of images

Segmentation first breaks the images into segments or regions, with the segments of the region having text or symbols. The segmented image is separately applied to two different CNN-based models. Each model produces text boxes where potential text might exist. Then, a selective NMS algorithm is applied to the output of each model to produce a final group of text regions. These text regions are analyzed and actions taken.

Flow meter

A flow meter includes a background pattern disposed behind a drip chamber, an image sensor, and a processor. The image sensor has a field of view and is configured to view the drip chamber within the field of view. The processor is coupled to the image sensor to receive image data therefrom and captures, using the image sensor, an image of the drip chamber and at least a portion of the background pattern, examines the image, and adjusts a flow rate of fluid flowing through a fluid line in accordance with the examination of the image.

Scene understanding using a neurosynaptic system

Embodiments of the invention provide a method for scene understanding based on a sequence of image frames. The method comprises converting each pixel of each image frame to neural spikes, and extracting features from the sequence of image frames by processing neural spikes corresponding to pixels of the sequence of image frames. The method further comprises encoding the extracted features as neural spikes, and classifying the extracted features.

Automated review of communications

A method of automated review of communications comprises: receiving, by a computer system, a document from a requestor application; extracting layout information and text from the document; extracting, based on the layout information, values of one or more predefined data items from the text of the document; producing a document validation result by analyzing the one or more data items; embedding, into the document, one or more human-readable comments reflecting the document validation result; and forwarding, to the requestor application, the document comprising the one or more human readable comments.

System and method to extract information from unstructured image documents

The present disclosure relates to a system and method to extract information from unstructured image documents. The extraction technique is content-driven and not dependent on the layout of a particular image document type. The disclosed method breaks down an image document into smaller images using the text cluster detection algorithm. The smaller images are converted into text samples using optical character recognition (OCR). Each of the text samples is fed to a trained machine learning model. The model classifies each text sample into one of a plurality of pre-determined field types. The desired value extraction problem may be converted into a question-answering problem using a pre-trained model. A fixed question is formed on the basis of the classified field type. The output of the question-answering model may be passed through a rule-based post-processing step to obtain the final answer.

Two-dimensional Symbols For Facilitating Machine Learning Of Written Chinese Language Using Logosyllabic Characters

Two-dimensional symbol for facilitating machine learning of written Chinese language using logosyllabic characters is disclosed. The two-dimensional symbol comprises a matrix of N×N pixels of data containing a “super-character” that represents a specific form and meaning of written Chinese language. The matrix is divided into M×M sub-matrices with each sub-matrix containing (N/M)×(N/M) pixels. Each of sub-matrix represents one logosyllabric character defined in a standard set (e.g., GB18030). “Super-character” is recognized in a Cellular Neural Networks or Cellular Nonlinear Networks (CNN) based computing system via an image processing technique such as convolution neural networks algorithm. “Super-character” contains a minimum of two and a maximum of M×M characters for representing written Chinese language including, but not necessarily limited to, compounded phrases, idioms, proverbs, written passages, sentences, poems, paragraphs, articles (i.e., written works). N and M are positive integers or whole numbers, and N is preferably a multiple of M.

Machine learning data extraction algorithms

Embodiments of the present disclosure pertain to extracting data corresponding to particular data types using machine learning algorithms. In one embodiment, a method includes receiving an image in a backend system, sending the image to an optical character recognition (OCR) component, and in accordance therewith, receiving a plurality of characters recognized in the image. The character set is matched against known values to generate candidate character strings. The character set is processed by one or more machine learning algorithms to produce features. For each candidate character string, the features are then processed by a random forest model to determine a final character string.

Automated honeypot creation within a network

Systems and methods for managing Application Programming Interfaces (APIs) are disclosed. Systems may involve automatically generating a honeypot. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving, from a client device, a call to an API node and classifying the call as unauthorized. The operation may include sending the call to a node-imitating model associated with the API node and receiving, from the node-imitating model, synthetic node output data. The operations may include sending a notification based on the synthetic node output data to the client device.

Document classification neural network and ocr-to-barcode conversion

Document classification techniques are disclosed that convert text content extracted from documents into graphical images and apply image classification techniques to the images. A graphical image of the text (such as a bar-code) may be generated and applied to improve the performance of document classification, bypassing NLP and utilizing more efficient localized OCR than in conventional approaches.

Methods and apparatus for capturing, processing, training, and detecting patterns using pattern recognition classifiers

A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.

Generating numeric embeddings of images

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating numeric embeddings of images. One of the methods includes obtaining training images; generating a plurality of triplets of training images; and training a neural network on each of the triplets to determine trained values of a plurality of parameters of the neural network, wherein training the neural network comprises, for each of the triplets: processing the anchor image in the triplet using the neural network to generate a numeric embedding of the anchor image; processing the positive image in the triplet using the neural network to generate a numeric embedding of the positive image; processing the negative image in the triplet using the neural network to generate a numeric embedding of the negative image; computing a triplet loss; and adjusting the current values of the parameters of the neural network using the triplet loss.

Determining an item that has confirmed characteristics

In various example embodiments, a system and method for determining an item that has confirmed characteristics are described herein. An image that depicts an object is received from a client device. Structured data that corresponds to characteristics of one or more items are retrieved. A set of characteristics is determined, the set of characteristics being predicted to match with the object. An interface that includes a request for confirmation of the set of characteristics is generated. The interface is displayed on the client device. Confirmation that at least one characteristic from the set of characteristics matches with the object depicted in the image is received from the client device.

Generating navigation data

Navigation data is generated by receiving ( 502 ) a new experience data set ( 321 ) relating to a new experience capture. At least one stored experience data set ( 320 ) relating to at least one previous experience capture is also received ( 504 ). An experience data set includes a set of nodes, with each node comprising a series of visual image frames taken over a series of time frames. A candidate set of said nodes is obtained ( 506 ) from the stored experience data set that potentially matches a said node in the new experience data set, and then a check ( 508 ) if performed to see if a node in the candidate set matches the node in the new experience data set. If the result of the checking is positive then data relating to the matched nodes is added ( 510 ) to a place data set useable for navigation, the place data set indicating that said nodes in different said experience data sets relate to a same place.

Processing images using deep neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

Using multiple cameras to perform optical character recognition

The subject matter of this specification can be implemented in, among other things, a method that includes receiving a first image from a first camera depicting a first view of a physical item, where the physical item displays a plurality of characters. The method includes receiving a second image from a second camera depicting a second view of the physical item. The method includes performing optical character recognition on the first image to identify first characters and a first layout in the first image and on the second image to identify second characters and a second layout in the second image. The method includes combining the first characters with the second characters by comparing the first characters with the second characters and the first layout with the second layout. The method includes storing the combined first and second characters.

Determining a document type of a digital document

Disclosed are systems and method for determining document type of a digital document. An example method comprises: executing a first MLA classifier in order to determine a document type for a digital document, wherein the first MLA classifier is associated with a first hierarchical order of execution, and wherein the first MLA classifier is trained on a first trained dataset containing a first document type and a second document type, wherein the first document type is confidently predictable by the first MLA classifier and the second document type is not confidently predictable by the first MLA classifier; and responsive to determining that the first MLA classifier produced the second document type for the digital document, executing a second MLA classifier in order to determine the document type for the digital document, wherein the second MLA classifier is associated with a second hierarchical order of execution following the first hierarchical order of execution, and wherein the second MLA classifier is trained on a second trained dataset containing no documents of the first document type.

Information processing apparatus, method for controlling information processing apparatus, and storage medium

An information processing apparatus comprising: at least one processor programmed to cause the apparatus to: hold label information regarding presence of a target object, the label information being set for the target object in an image; obtain a reliability of the label information; cause a display apparatus to display the label information and an image corresponding to the label information in the image, based on the reliability; accept an operation made by a user; and modify the label information based on the operation.

Semi-supervised price tag detection

A method comprising: training a price tag detector, comprising a gross feature detector and a classifier, to automatically detect a price tag in an image, by: a) training the gross feature detector using supervised learning with labeled images, and b) training the classifier using a two-phase hybrid learning process comprising: c) applying an initial supervised learning using the labeled images, yielding a semi-trained version of the classifier, and d) applying a subsequent unsupervised learning using unlabeled images, yielding a fully trained version of the classifier, wherein applying the unsupervised learning comprises: for each unlabeled image: i) detecting multiple price tag hypotheses using the gross feature detector, ii) classifying each price tag hypothesis using the semi-trained classifier, ii) rating each classification based contextual data extracted from the unlabeled image, iv) retraining the semi-trained classifier with the rated classifications, and repeating steps ii) through iv) until the reclassification converges.

Generating variations of a known shred

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.

System and method for recognizing credit card number and expiration date using terminal device

Disclosed herein is a system and method for recognizing the credit card number and expiration date of a credit card using a terminal device. More specifically, the method may include the steps of (a) obtaining an image of the card through a camera, (b) performing position detection and number recognition on card numbers within the image obtained at the step (a), and (c) performs position detection and number recognition on expiration date numbers within the image obtained at the step (a). In accordance with an embodiment of the present invention, a recognition rate can be improved compared to an image processing-based technology.

Automated signature extraction and verification

A system for extraction and verification of handwritten signatures from arbitrary documents. The system comprises one or more computing devices configured to: receive a digital image of a document; remove a subset of words from the digital image identified via OCR; determine a plurality of regions of connected markings that remain in the digital image; based at least in part on a pixel density or proximity to an anchor substring of each region, determine that a region contains a handwritten signature; extract first image data of the region containing a handwritten signature from the digital image; retrieve second image data of a confirmed example signature for a purported signer of the handwritten signature; and based on a comparison of the first image data with the second image data, forward a determination of whether the first image data and second image data are similar.

Content evaluation based on machine learning and engagement metrics

Techniques for machine learning analysis are provided. A machine learning (ML) model is trained to identify appropriate documents based on lexical knowledge of target groups. A lexical knowledge of a set of users is determined. Additionally, a first document of a plurality of documents is selected by processing the determined level of lexical knowledge using the ML model. The first document is presented to the set of users. A level of engagement of the set of users is then determined. Upon determining that the level of engagement is below a predefined threshold, a second document of the plurality of documents is selected using the ML model.

Learning combinations of homogenous feature arrangements

One embodiment provides a method comprising receiving an input, and classifying the input utilizing a learned linear combination of multi-dimensional filters. Each multi-dimensional filter identifies a multi-dimensional pattern of a homogenous feature. The method further comprises generating an output indicative of a classification of the input.

Detecting a fragmented object in an image

An example process described herein may involve capturing an image including a document; identifying a first part of the document, wherein the first part of the document is identified based on detecting an outline of the first part of the document; analyzing a first region of the image determined in relation to the first part of the document to detect a second part of the document based on an outline of the second part of the document; identifying the second part of the document based on detecting the first part of the document and analyzing the first region; combining the first part of the document with the second part of the document to generate object data associated with the document, wherein the object data includes data representative of a gap between the first part of the document and the second part of the document; and performing an action related to the object data.

Media management system for video data processing and adaptation data generation

In various embodiments, methods and systems for implementing a media management system, for video data processing and adaptation data generation, are provided. At a high level, a video data processing engine relies on different types of video data properties and additional auxiliary data resources to perform video optical character recognition operations for recognizing characters in video data. In operation, video data is accessed to identify recognized characters. A video OCR operation to perform on the video data for character recognition is determined from video character processing and video auxiliary data processing. Video auxiliary data processing includes processing an auxiliary reference object; the auxiliary reference object is an indirect reference object that is a derived input element used as a factor in determining the recognized characters. The video data is processed based on the video OCR operation and based on processing the video data, at least one recognized character is communicated.

Optimizing inference time of entity matching models

Methods, systems, and computer-readable storage media for receiving input data including a set of entities of a first type and a set of entities of a second type, providing a set of features based on entities of the first type, the set of features including features expected to be included in entities of the second type, filtering entities of the second type based on the set of features to provide a sub-set of entities of the second type, and generating an output by processing the set of entities of the first type and the sub-set of entities of the second type through a ML model, the output comprising a set of matching pairs, each matching pair in the set of matching pairs comprising an entity of the set of entities of the first type and at least one entity of the sub-set of entities of the second type.

Machine Learning System for Summarizing Tax Documents With Non-Structured Portions

Technologies for summarizing tax documents that include an unstructured portion, such as K1 filings. The system extracts data from both the structured information, such as a K1 facepage, and unstructured information, such as whitepaper statement(s). The system includes machine learning model(s) to determine the information to be extracted from the unstructured information. The machine learning model(s) generate a confidence level associated with the extracted unstructured information that represents a prediction on how likely the extracted unstructured information was accurately extracted. The system generates a document in an electronic interchange format that represents both the structured and unstructured information in the analyzed tax document.

Medical evaluation system and method for use therewith

A medical evaluation system operates by: receiving a set of medical scans of a medical scan protocol captured for a patient, the set of medical scans corresponding to a proper subset of a plurality of sequence types; generating abnormality data by performing an inference function on the set of medical scans, wherein the inference function utilizes a computer vision model trained on a plurality of medical scans corresponding to the proper subset of the plurality of sequence types; calculating a confidence score for the abnormality data; generating first additional sequence data, wherein when the confidence score compares unfavorably to a confidence score threshold, the first additional sequence data indicates at least one first additional medical scan of the patient, corresponding to a first at least one of the plurality of sequence types not included in the proper subset of the plurality of sequence types, and when the confidence score compares favorably to the confidence score threshold, the first additional sequence data indicates no further medical scans of the patient; and transmitting the first additional sequence data.

Heat map generating system and methods for use therewith

A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of global labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the global labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Heat map visualization data can be generated for transmission to a client device based on the probability matrix data that indicates, for each of the set of abnormality classes, a color value for each pixel of the new medical scan.

Augmenting video data to present real-time metrics

Systems and methods are described for augmenting video data based on automated identification of one or more objects depicted in the video data. One or more classification models may identify an object of interest in video data. An aggregated duration count may be maintained that reflects a length of time that the object of interest has been depicted in the video data. This duration or additional metric data derived in part from the duration may be displayed in association with display of the video data and continuously updated during playback of the video data.

Optical character recognition using end-to-end deep learning

Disclosed herein are system, method, and computer program product embodiments for optical character recognition using end-to-end deep learning. In an embodiment, an optical character recognition system may train a neural network to identify characters of pixel images and to assign index values to the characters. The neural network may also be trained to identify groups of characters and to generate bounding boxes to group these characters. The optical character recognition system may then analyze documents to identify character information based on the pixel data and produce a segmentation mask and one or more bounding box masks. The optical character recognition system may supply these masks as an output or may combine the masks to generate a version of the received document having optically recognized characters.

Automatic protocol discovery using text analytics

A computing system for learning a device type and message formats used by a device is provided. The computing system includes an interface and a processor. The interface is receptive of documents describing identification information and communication and application protocols of devices. The processor is coupled with the interface to obtain rules of network packet analysis using document analytics and identify identification information and communication and application protocols of network messages from devices using the rules.

METHOD FOR CHARACTER RECOGNITION, ELECTRONIC DEVICE, AND STORAGE MEDIUM

The disclosure discloses a method for character recognition, an electronic device, and a storage medium. The technical solution includes: obtaining a test sample image and a test sample character both corresponding to a test task; performing fine-tuning on a trained meta-learning model based on the test sample image and the test sample character to obtain a test task model; obtaining a test image corresponding to the test task; and generating a test character corresponding to the test image by inputting the test image into the test task model. 1. A method for character recognition , comprising:obtaining a test sample image and a test sample character both corresponding to a test task;performing fine-tuning on a trained meta-learning model based on the test sample image and the test sample character to obtain a test task model;obtaining a test image corresponding to the test task; andgenerating a test character corresponding to the test image by inputting the test image into the test task model.2. The method of claim 1 , further comprising:obtaining a first training sample image and a first training sample character both corresponding to a training task;training a meta-learning model to be trained based on the first training sample image and the first training sample character to obtain a training task model;obtaining a second training sample image and a second training sample character both corresponding to the training task; andupdating the meta-learning model to be trained based on the second training sample image, the second training sample character and the training task model to obtain the trained meta-learning model.3. The method of claim 2 , wherein updating the meta-learning model to be trained based on the second training sample image claim 2 , the second training sample character and the training task model to obtain the trained meta-learning model comprises:generating a predicted training sample character corresponding to the second training sample image ...

Automated methods and systems for locating document subimages in images to facilitate extraction of information from the located document subimages

The present document is directed to methods and subsystems that identify and characterize document-containing subimages in a document-containing image. In one implementation, each type of document is modeled as a set of features that are extracted from a set of images known to contain the document. To locate and characterize a document subimage in an image, the currently described methods and subsystems extract features from the image and then match model features of each model in a set of models to the extracted features to select the model that best corresponds to the extracted features. Additional information contained in the selected model is then used to identify the location of the subimage corresponding to the document and to process the document subimage to correct for a variety of distortions and deficiencies in order to facilitate subsequent data extraction from the corrected document subimage.

Domain-Specific Phrase Mining Method, Apparatus and Electronic Device

A domain-specific phrase mining method, apparatus and electronic device are provided. A specific implementation includes: performing word vector conversion on a domain-specific phrase in a target text to obtain a first word vector, and performing word vector conversion on an unknown phrase in the target text to obtain a second word vector, where the domain-specific phrase is a phrase in a domain to which the target text belongs; obtaining a word vector space formed by the first and second word vectors, and identifying a preset quantity of target word vectors around the second word vector in the word vector space; determining, based on similarity values indicative of similarity between the preset quantity of target word vectors and the second word vector, whether the unknown phrase is a phrase in the domain to which the target text belongs.

Text refinement network

Systems and methods for text segmentation are described. Embodiments of the inventive concept are configured to receive an image including a foreground text portion and a background portion, classify each pixel of the image as foreground text or background using a neural network that refines a segmentation prediction using a key vector representing features of the foreground text portion, wherein the key vector is based on the segmentation prediction, and identify the foreground text portion based on the classification.

Method of training models in ai and electronic device

A method of training models in AI and an electronic device are disclosed, the electronic device is connected to other electronic devices and a controller, each electronic device is deployed with a single initial machine learning model and can obtain a prediction accuracy and weightings of neurons of the trained machine learning model. The controller determines new weightings from a plurality of the received weightings according to a preset rule and a plurality of received prediction accuracies. Each electronic device updates the weightings of neurons of the trained machine learning model to the new weightings. An electronic device is also disclosed. The method reduces a cost of training a machine learning model, utilizes network resources more efficiently, and improves an accuracy of the machine learning model.

CHARACTER RECOGNITION METHOD, MODEL TRAINING METHOD, RELATED APPARATUS AND ELECTRONIC DEVICE

A character recognition method, a model training method, a related apparatus and an electronic device are provided. The specific solution is: obtaining a target picture; performing feature encoding on the target picture to obtain a visual feature of the target picture; performing feature mapping on the visual feature to obtain a first target feature of the target picture, where the first target feature is a feature that has a matching space with a feature of character semantic information of the target picture; inputting the first target feature into a character recognition model for character recognition to obtain a first character recognition result of the target picture.

Method for determining annotation capability information, related apparatus and computer program product

A method and apparatus for determining annotation capability information, an electronic device, a computer readable storage medium and a computer program product are provided. An implementation of the method includes: determining a trial annotation object according to an annotation demand for a to-be-annotated task; determining trial annotation data, according to the annotation demand and a preset trial annotation requirement; and determining a trial annotation duration according to an attribute of the trial annotation object, and determining annotation capability information of the trial annotation object according to an annotation result of the trial annotation object annotating the trial annotation data within the trial annotation duration.

Organizational data enrichment

In an example embodiment, a fuzzy join operation is performed by, for each pair of records, evaluating a first plurality of features for both records in the pair of records by calculating term frequency-inverse term frequency (TF-IDF) for each token of each field relevant to each feature and based on the calculated TF-IDF for each token of each field relevant to each feature, computing a similarity score based on the similarity function by adding a weight assigned to the TF-IDF for any token that appears in both records. Then a graph data structure is created, having a node for each record in the plurality of records and edges between each of the nodes, except, for each record pair having a similarity score that does not transgress a first threshold, causing no edge between the nodes for the record pair to appear in the graph data structure;

Organizational logo enrichment

In an example embodiment, a web page is obtained using a web page address stored in a first record and is parsed to extract one or more images from the web page along with a second plurality of features for each of the one or more images from the web page. Information about each image of the web page and the extracted second plurality of features for the web page are input into a supervised machine learning classifier to calculate a logo confidence score for each image of the web page, the logo confidence score indicating the probability that the image is an organization logo. In response to a particular image in the web page having a logo confidence score transgressing a first threshold, the particular image is injected into an organization logo field of the first record.

Neural network-based classification method and classification device thereof

A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.

AUTOMATICALLY SCALABLE SYSTEM FOR SERVERLESS HYPERPARAMETER TUNING

A scalable system and method for completing a model task using a serverless architecture is disclosed. The system may include memory storing instructions and one or more processors. The method may include receiving a request to complete a model task; retrieving a first model and a first hyperparameter based on the request; provisioning computing resources to a first development instance configured to train the first model based on the first hyperparameter and the model task; training, by the first development instance, an instance of the first model to produce a trained model and terminating said training upon satisfaction of a training criterion; receiving the trained model and a first performance metric; receiving a second performance metric associated with a second model; and terminating the development instance based on a determination that the termination condition is satisfied based on at least one of the first and second performance metrics. 120-. (canceled)21. A scalable system for completing a model task using a serverless architecture , the system comprising: memory for storing instructions; and', receiving a request to complete a model task;', 'retrieving a first model from a model storage by selecting, based on the model task, the first model in an index of stored models;', 'retrieving a first hyperparameter based on the first model and the model task;', 'provisioning computing resources to a first development instance configured to train the first model based on the first hyperparameter and the model task;', 'creating an instance of the first model from the first development instance;', 'retrieving, by the first development instance, training data comprising synthetic data based on actual data;', 'training the instance of the first model by the first development instance using the training data to obtain a first trained model;', 'terminating, by the first development instance, the training upon satisfaction of a training criterion, wherein the training ...

MODEL TRAINING METHOD AND APPARATUS, FONT LIBRARY ESTABLISHMENT METHOD AND APPARATUS, AND STORAGE MEDIUM

A method for training a font generation model is described below. A source domain sample character and a target domain association character are input into an encoder of the font generation model to obtain a sample character content feature and an association character style feature. The sample character content feature and the association character style feature are input into an attention mechanism network to obtain a target domain style feature. The sample character content feature and the target domain style feature are input into a decoder to obtain a target domain generation character. The target domain generation character and at least one of a target domain sample character or the target domain association character are input into a loss analysis network of the font generation model to obtain a model loss, and a parameter of the font generation model is adjusted according to the model loss. 1. A method for training a font generation model , comprising:inputting a source domain sample character and a target domain association character of the source domain sample character into an encoder of the font generation model to obtain a sample character content feature and an association character style feature;inputting the sample character content feature and the association character style feature into an attention mechanism network of the font generation model to obtain a target domain style feature;inputting the sample character content feature and the target domain style feature into a decoder of the font generation model to obtain a target domain generation character; andinputting the target domain generation character and at least one of a target domain sample character or the target domain association character into a loss analysis network of the font generation model to obtain a model loss, and adjusting a parameter of the font generation model according to the model loss.2. The method according to claim 1 , wherein the attention mechanism network comprises ...

METHOD AND APPARATUS FOR EXTRACTING INFORMATION ABOUT A NEGOTIABLE INSTRUMENT, ELECTRONIC DEVICE AND STORAGE MEDIUM

Provided are a method and apparatus for extracting information about a negotiable instrument, an electronic device and a storage medium. The method includes inputting a to-be-recognized negotiable instrument into a pretrained deep learning network and obtaining a visual image corresponding to the to-be-recognized negotiable instrument through the deep learning network; 1. A method for extracting information about a negotiable instrument , comprising:inputting a to-be-recognized negotiable instrument into a pretrained deep learning network, and obtaining a visual image corresponding to the to-be-recognized negotiable instrument through the deep learning network;matching the visual image corresponding to the to-be-recognized negotiable instrument with a visual image corresponding to each negotiable-instrument template in a preconstructed base template library; andin response to the visual image corresponding to the to-be-recognized negotiable instrument successfully matching a visual image corresponding to one negotiable-instrument template in the base template library, extracting structured information of the to-be-recognized negotiable instrument by using the one negotiable-instrument template.2. The method of claim 1 , further comprising:in response to the visual image corresponding to the to-be-recognized negotiable instrument failing to match the visual image corresponding to each negotiable-instrument template in the base template library, constructing, based on the visual image corresponding to the to-be-recognized negotiable instrument, a negotiable-instrument template corresponding to the to-be-recognized negotiable instrument, and registering the negotiable-instrument template corresponding to the to-be-recognized negotiable instrument in the base template library.3. The method of claim 1 , wherein matching the visual image corresponding to the to-be-recognized negotiable instrument with the visual image corresponding to each negotiable-instrument template ...

AUGMENTED REALITY INTERFACE FOR ASSISTING A USER TO OPERATE AN ULTRASOUND DEVICE

Aspects of the technology described herein relate to techniques for guiding an operator to use an ultrasound device. Thereby, operators with little or no experience operating ultrasound devices may capture medically relevant ultrasound images and/or interpret the contents of the obtained ultrasound images. For example, some of the techniques disclosed herein may be used to identify a particular anatomical view of a subject to image with an ultrasound device, guide an operator of the ultrasound device to capture an ultrasound image of the subject that contains the particular anatomical view, and/or analyze the captured ultrasound image to identify medical information about the subject. 1. An apparatus , comprising: obtain an ultrasound image of a subject;', 'identify a value of an ejection fraction of the subject at least in part by analyzing the ultrasound image using a deep learning technique; and', 'form a composite image including the ultrasound image and the value of the ejection fraction., 'at least one processor configured to2. The apparatus of claim 1 , wherein the at least one processor is configured to identify the value of the ejection fraction of the subject at least in part by identifying at least one anatomical feature of the subject in the ultrasound image using the deep learning technique.3. The apparatus of claim 2 , wherein the at least one processor is configured to identify the at least one anatomical feature of the subject at least in part by providing the ultrasound image as an input to a multi-layer neural network.4. The apparatus of claim 2 , wherein the at least one anatomical feature is a heart ventricle claim 2 , and wherein the at least one processor is configured to identify the heart ventricle of the subject at least in part by analyzing the ultrasound image using a multi-layer neural network comprising at least one layer selected from the group consisting of: a pooling layer claim 2 , a rectified linear units (ReLU) layer claim 2 , a ...

Hierarchical Category Classification Scheme Using Multiple Sets of Fully-Connected Networks With A CNN Based Integrated Circuit As Feature Extractor

CNN based integrated circuit is configured with a set of pre-trained filter coefficients or weights as a feature extractor of an input data. Multiple fully-connected networks (FCNs) are trained for use in a hierarchical category classification scheme. Each FCN is capable of classifying the input data via the extracted features in a specific level of the hierarchical category classification scheme. First, a root level FCN is used for classifying the input data among a set of top level categories. Then, a relevant next level FCN is used in conjunction with the same extracted features for further classifying the input data among a set of subcategories to the most probable category identified using the previous level FCN. Hierarchical category classification scheme continues for further detailed subcategories if desired.

Lens distortion correction using a neurosynaptic circuit

One or more embodiments provide a neurosynaptic circuit that includes multiple neurosynaptic core circuits that: perform image sharpening by converting a source image to a sharpened destination image by: taking as input a sequence of image frames of a video with one or more channels per frame, and representing the intensity of each pixel of each channel of each frame as neural spikes, and processing neural spike representations of the sharpened destination image for outputting a spike representation of the sharpened destination image.

Named entity recognition with convolutional networks

Methods and systems for recognizing named entities within the text of a document are provided. The methods and systems may include receiving a document image and recognized text of the document image. A feature map of the document image may be created, a tagged map may be created, and locations of tags within the tagged map may be estimated using a machine learning model. Named entities with the recognized text may be recognized based on the one or more locations of the tags. In some embodiments, the machine learning model is a convolutional neural network. In further embodiments, creating the feature map may include determining, for a subset of the cells of the feature map, one or more features of the recognized text contained in a corresponding portion of the document image.

Method and system for splicing and restoring shredded paper based on extreme learning machine

The present invention discloses a method and system for splicing and restoring shredded paper based on an extreme learning machine. The method includes: acquiring a shredded paper training sample to be spliced; extracting left and right boundary feature data of the training sample; training an extreme learning machine neural network model according to the left and right boundary feature data, to obtain a trained neural network model; acquiring a shredded paper test sample to be spliced; extracting left and right boundary feature data of the test sample; selecting a first piece of to-be-spliced shredded paper; selecting shredded paper with a highest degree of coincidence with the first piece of to-be-spliced shredded paper by the trained neural network model; determining whether the shredded paper with the highest degree of coincidence is correctly spliced to the first piece of to-be-spliced shredded paper; if yes, splicing shredded paper until all the shredded paper is spliced and restored; and if not, adopting manual marking, and continuing to select shredded paper with a highest degree of coincidence with the first piece of to-be-spliced shredded paper by the trained neural network model. The method and system for splicing and restoring shredded paper based on an extreme learning machine can well splice and restore shredded paper quickly. Disclosed is a method and system for splicing and restoring shredded paper based on an extreme learning machine (“ELM”). The method includes: acquiring a shredded paper training sample to be spliced; extracting left and right boundary feature data of the sample; training an ELM neural network model according to the feature data to obtain a trained neural network model (“TNNM”); acquiring a shredded paper test sample to be spliced; extracting feature data of the test sample; selecting a first piece of to-be-spliced shredded paper; selecting, by the TNNM, a shredded piece with a highest degree of coincidence with the first piece; ...

Overlapping cnn cache reuse in high resolution and streaming-based deep learning inference engines

A method optimizes Convolutional Neural Network (CNN) inference time for full resolution images. One or more processors divide a full resolution image into a plurality of partially overlapping sub-images. The processor(s) select, from the plurality of partially overlapping sub-images, a first sub-image and a second sub-image that overlap one another in an overlapping area. The processor(s) feed the first sub-image, including the overlapping area, into a Convolutional Neural Network (CNN) in order to create a first inference result for the first sub-image, where the CNN has been trained at a fine resolution. The processor(s) cache an inference result from the CNN for the overlapping area, and then utilize the cached inference result when inferring the second sub-image in the CNN. The processor(s) then identify a specific object in the full resolution image based on inferring the first sub-image and the second sub-image.

Robot Natural Language Term Disambiguation and Entity Labeling

A apparatus, e.g., a robot, that uses sensor inputs and physical actions to disambiguate terms in natural language commands and corresponding methods, systems, and computer programs encoded on computer storage media. A robot can receive a natural language command from a user having an ambiguous term that references a location or an entity in an environment of the robot. A user location indicator is identified from one or more sensor inputs. A location within the environment of the robot is computed using the location indicator identified from the one or more sensor inputs. Resolution data is computed using the computed location, wherein the resolution data resolves the reference of the ambiguous term. One or more actions are generated using the natural language command and the resolved reference of the ambiguous term, and the robot can execute the one or more actions.

NEURAL NETWORK IMAGE PROCESSING APPARATUS

A neural network image processing apparatus arranged to acquire images from an image sensor and to: identify a ROI containing a face region in an image; determine at plurality of facial landmarks in the face region; use the facial landmarks to transform the face region within the ROI into a face region having a given pose; and use transformed landmarks within the transformed face region to identify a pair of eye regions within the transformed face region. Each identified eye region is fed to a respective first and second convolutional neural network, each network configured to produce a respective feature vector. Each feature vector is fed to respective eyelid opening level neural networks to obtain respective measures of eyelid opening for each eye region. The feature vectors are combined and to a gaze angle neural network to generate gaze yaw and pitch values substantially simultaneously with the eyelid opening values. 1. A method comprising:identifying a face region in an image;determining a plurality of facial landmarks in the face region;determining, based at least in part on the plurality of facial landmarks, a pose of the face region;identifying, based at least in part on the pose, a first eye region and a second eye region within the face region;inputting the first eye region into a first neural network and the second eye region into a second neural network;receiving a first feature vector from the first neural network and a second feature vector from the second neural network;determining a first eyelid opening value based at least in part on the first feature vector and a second eyelid opening value based at least in part on the second feature vector;inputting the first eyelid opening value and the second eyelid opening value into a third neural network; andreceiving, from the third neural network, a gaze yaw value or a pitch value associated with the first eyelid opening value or the second eyelid opening value.2. The method of claim 1 , wherein the first ...

Characterization System and Method With Guided Defect Discovery

A system is disclosed, in accordance with one or more embodiment of the present disclosure. The system may include a controller including one or more processors configured to execute a set of program instructions. The set of program instructions may be configured to cause the processors to: receive images of a sample from a characterization sub-system; identify target clips from patch clips; prepare processed clips based on the target clips; generate encoded images by transforming the processed clips; sort the encoded images into a set of clusters; display sorted images from the set of clusters; receive labels for the displayed sorted images; determine whether the received labels are sufficient to train a deep learning classifier; and upon determining the received labels are sufficient to train the deep learning classifier, train the deep learning classifier via the displayed sorted images and the received labels. 1. A system comprising: receive one or more images of a sample from a characterization sub-system, wherein the one or more images include one or more patch clips;', 'identify one or more target clips from the one or more patch clips;', 'prepare one or more processed clips based on the one or more target clips;', 'generate one or more encoded images by transforming the one or more processed clips via an autoencoder;', 'sort the one or more encoded images into a set of clusters via a clustering algorithm;', 'display one or more sorted images from one or more of the set of clusters to a user via a user interface;', 'receive one or more labels for the one or more displayed sorted images from the user via the user interface; and', 'adjust one or more fabrication tools based on the received one or more labels., 'a controller including one or more processors configured to execute a set of program instructions stored in memory, the set of program instructions configured to cause the one or more processors to2. The system of claim 1 , wherein the preparing the one ...

Cross-modality neural network transform for semi-automatic medical image annotation

A cross-modality neural network transform for semi-automatic medical image annotation is provided. In various embodiments, an input medical image is mapped to a first vector in a text vector space. The first vector corresponds to the features of the medical image. A set of predetermined vectors is searched for a closest one of the predetermined vectors to the first vector. From the closest one of the predetermined vectors, one or more keywords is determined describing the input medical image.