Method for monitoring manufacture of assembly units

One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units ...

Systems and methods for generating graphical user interfaces

A system for generating graphical user interfaces. The system may include processors and storage devices storing instructions. The instructions may configure the one or more processors to perform operations including identifying a plurality of attributes from an image captured with a client device, identifying a plurality of first results based on the attributes, generating a first graphical user interface for display in the client device. The first graphical user interface may include a plurality of result icons corresponding to a subset of the first results having confidence scores above a threshold, a plurality of filter icons displaying options, and a search button. The operations may also include receiving a selection of at least one of the result icons or at least one of the filter icons, performing a search, based on the selection, and generating a second graphical user interface.

METHOD FOR EXTRACTING INSTRUCTIONS FOR MONITORING AND/OR CONTROLLING A CHEMICAL PLANT FROM UNSTRUCTURED DATA

The present invention is in the field of computer-implemented methods for monitoring or controlling a chemical plant. It relates to a computer-implemented method for monitoring and/or controlling a chemical plant comprising (a1) providing unstructured data containing instructions for monitoring and/or controlling a chemical plant, (a2) providing information about the chemical plant at least including information of the geographical location of the plant or the compound handled in the plant through an interface, (b1) providing the unstructured data and the information about the chemical plant to a model suitable for extracting the instructions from the structured data, (b2) obtaining from the model instruction together with metadata including the applicability of the instruction related to at least one of time period, a geographical scope, or the compounds to be handled in the plant, and (c) outputting the instructions received from the model.

SYSTEM AND METHOD FOR DETERMINING TARGET FEATURE FOCUS IN IMAGE-BASED OVERLAY METROLOGY

A metrology system includes one or more through-focus imaging metrology sub-systems communicatively coupled to a controller, where the controller includes one or more processors. The one or more processors may be configured receive a plurality of training images captured at one or more focal positions. The one or more processors may further generate a machine learning classifier based on the plurality of training images captured at one or more focal positions. The one or more processors may further receive one or more target feature selections for one or more target overlay measurements corresponding to one or more target features of a target specimen. The one or more processors may further determine one or more target focal positions based on the one or more target feature selections using the machine learning classifier. The one or more processors may further receive one or more target images captured at the one or more target focal positions, the one or more target images including the ...

Detail-preserving image editing techniques

Systems and methods combine an input image with an edited image generated using a generator neural network to preserve detail from the original image. A computing system provides an input image to a machine learning model to generate a latent space representation of the input image. The system provides the latent space representation to a generator neural network to generate a generated image. The system generates multiple scale representations of the input image, as well as multiple scale representations of the generated image. The system generates a first combined image based on first scale representations of the images and a first value. The system generates a second combined image based on second scale representations of the images and a second value. The system blends the first combined image with the second combined image to generate an output image.

СПОСОБ, ТЕРМИНАЛ И СИСТЕМА ДЛЯ БИОМЕТРИЧЕСКОЙ ИДЕНТИФИКАЦИИ

Изобретение относится к области биометрической идентификации. Технический результат заключается в повышении уровня защиты от несанкционированного доступа, повышении быстродействия и надежности идентификации. Способ биометрической идентификации содержит этапы, на которых: активируют в терминале для биометрической идентификации режим поиска человеческого лица на цветных изображениях, полученных из видеопотока от одной камеры из стереокамеры; осуществляют предварительную обработку изображений со стереокамеры и инфракрасной или тепловой камеры терминала; обнаруживают и отслеживают лицо человека в изображении с одной камеры из стереокамеры и определяют его размеры и координаты; осуществляют поиск лица человека в изображении с инфракрасной или тепловой камеры, синхронизированном с изображением с цветной камеры, и определяют его размеры и координаты; сравнивают размеры и координаты лица человека, определенные для изображения с цветной камеры и изображения с инфракрасной или тепловой камеры, и ...

Dynamic self-learning medical image method and system

A method and system for creating a dynamic self-learning medical image network system, wherein the method includes receiving, from a first node initial user interaction data pertaining to one or more user interactions with the one or more initially obtained medical images; training a deep learning algorithm based at least in part on the initial user interaction data received from the node; and transmitting an instance of the trained deep learning algorithm to the first node and/or to one or more additional nodes, wherein at each respective node to which the instance of the trained deep learning algorithm is transmitted, the trained deep learning algorithm is applied to respective one or more subsequently obtained medical images in order to obtain a result.

Data processing for machine learning using a graphical user interface

Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.

СИСТЕМА РАСПОЗНАВАНИЯ ЦИФРОБУКВЕННОЙ СОСТАВЛЯЮЩЕЙ МАТРИЧНОГО КОДА НА ПОВЕРХНОСТИ ЗАГОТОВОК

Изобретение относится к системам технического зрения для контроля качества печати кодов маркировки. Система распознавания цифробуквенной составляющей матричного кода на поверхности заготовок включает управляющее устройство, комплексы подсветки, высокоскоростные камеры, датчики обнаружения, программное обеспечение, конвейер; энкодер, источники бесперебойного питания, локальный сервер с коммутатором Ethernet. Управляющим устройством является программируемый логический контроллер (ПЛК), вход которого соединен с выходом датчиков обнаружения, имеющего порт ввода/вывода информации для двухсторонней передачи данных с модулем системы HMI, соединенным через порт ввода/вывода информации с переключателем, соединенным с контроллерами технического зрения, контроллеры технического зрения соединены через порты ввода/вывода информации с высокоскоростными камерами и портом вывода информации, и соединены с входом в комплекс подсветки, каждый контроллер технического зрения подключен к Ethernet коммутатору ...

БИОМЕТРИЧЕСКИЙ ТЕРМИНАЛ РАСПОЗНАВАНИЯ ЛИЦ

Полезная модель относится к области распознавания биометрических шаблонов, относящихся к человеку, в изображениях или видеоданных, в частности, к распознаванию лица. Разработан биометрический терминал распознавания лиц, содержащий корпус с установленными в нем и связанными проводными линиями связи блоком освещения, блоком приема изображения, блоком управления и обработки, характеризующийся тем, что блок освещения выполнен с возможностью освещать лицо видимым светом, инфракрасным светом, структурированным светом, блок приема изображения выполнен с возможностью приема изображения лица в видимом свете, в инфракрасном свете и структурированном свете, блок управления и обработки выполнен с возможностью командовать блоку освещения освещать лицо видимым светом, инфракрасным светом и структурированным светом, с возможностью проверки витальности распознаваемого лица на основании изображения, полученного от блока приема изображения в видимом свете, инфракрасном свете, структурированном свете, блок ...

PERFORMANCE GRINDING SOLUTIONS

The present application relates to systems and methods for obtaining real-time abrasion data. An example computer-implemented method could include receiving, at a computing device, sensor data from one or more sensors. The one or more sensors are disposed in proximity to an abrasive product or a workpiece associated with the abrasive product. The one or more sensors are configured to collect abrasion operational data associated with an abrasive operation involving the abrasive product or the workpiece. The computer-implemented method could further include training, based on the sensor data, a machine learning system to determine product specific information of the abrasive product and/or workpiece specific information. The computer-implemented method could also include providing the trained machine learning system using the computing device.

Systems and methods for classification of arterial image regions and features thereof

In part, the disclosure relates to methods, and systems suitable for evaluating image data from a patient on a real time or substantially real time basis using machine learning (ML) methods and systems. Systems and methods for improving diagnostic tools for end users such as cardiologists and imaging specialists using machine learning techniques applied to specific problems associated with intravascular images that have polar representations. Further, given the use of rotating probes to obtain image data for OCT, IVUS, and other imaging data, dealing with the two coordinate systems associated therewith creates challenges. The present disclosure addresses these and numerous other challenges relating to solving the problem of quickly imaging and diagnosis a patient such that stenting and other procedures may be applied during a single session in the cath lab.

Methods and systems for tuning a static model

Methods and systems are provided for tuning a static model with multiple operating points to adjust model performance without retraining the model or triggering a new regulatory clearance. In one embodiment, a method comprises, responsive to a request to tune a model, obtaining a tuning dataset including a set of medical images, executing the model using the set of medical images as input to generate model tuning output, and determining, for each operating point of a set of operating points, a set of tuning metric values based on the tuning dataset and the model tuning output relative to each operating point. An operating point from the set of operating points may be selected based on each set of tuning metric values and, upon a request to analyze a subsequent medical image, a representation of a finding output from the static model executed at the selected operating point.

СПОСОБЫ И СИСТЕМЫ ДЛЯ АВТОМАТИЧЕСКОГО РАСПОЗНАВАНИЯ ОБЪЕКТОВ И ПРОВЕРКИ ПОДЛИННОСТИ

Изобретение относится к системам и способам автоматического распознавания и проверки подлинности объектов. Технический результат заключается в увеличении точности распознавания и установления подлинности объекта за счет учета эффектов старения при распознавании объектов. Технический результат достигается за счет выполнения следующих этапов способа: получение данных объекта, представляющих собой отличительные характеристики физического объекта; обработка данных объекта посредством основанного на машинном обучении процесса распознавания объектов для получения отличительных данных, представляющих собой устойчивые к коллизиям виртуальные представления физического объекта; сравнение по меньшей мере одного параметра из числа отличительных данных и полученного из них посредством применения к ним предварительно заданной шифровальной хеш-функции оригинального значения хеша с соответствующими справочными данными, сохраненными в одном или нескольких хранилищах данных с ограниченным доступом; выдача ...

Устройство и способ дешифровки паттернов поведения животных в длительном актографическом эксперименте

Группа изобретений относится к медицине, а именно к программно-аппаратному комплексу дешифровки паттернов поведения животных и способу дешифровки поведения животного с помощью этого комплекса. Комплекс содержит группу регистрирующих камер (14) для размещения лабораторных животных (10), подсистему индивидуального видеонаблюдения (3) за животными, подсистему сейсмоакустической регистрации колебаний дна и стенок каждой из камер и/или подсистему акустической регистрации издаваемых животными звуков, подсистему синхронизации потока видеоданных и потоков акустических и/или сейсмоакустических данных. Вызываемые двигательной активностью животного колебания дна и стенок камер регистрируются сейсмоакустическим датчиком в составе подсистемы сейсмоакустической регистрации (15). Аналоговый сигнал от сейсмоакустического датчика проходит каскад фильтрации и предусиления перед попаданием в аналогово-цифровой преобразователь (7). Подсистема акустической регистрации звуков (2) включает акустические сенсоры ...

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.

Systems and methods for managing meat cut quality

In some embodiments, apparatuses and methods are provided herein useful to ensuring quality of meat cuts. In some embodiments, a system for ensuring quality of meat cuts comprises a capture device comprising an image capture device configured to capture an image of a cut of meat, a depth sensor configured to capture depth data, a transceiver configured to transmit the image and the depth data, a microcontroller configured to control the image capture device, the depth sensor, and the transceiver, a database configured to store meat cut specifications, and the control circuit configured to receive, from the capture device, the image and the depth data, retrieve, from the database, a meat cut specification, evaluate the image of the cut of meat and the depth data associated with the cut of meat, and classify the cut of meat.

Quick data exploration

A computer-implemented method for quick data exploration of data to be uploaded may be provided. The method (100) comprises uploading from a local system a first data set (102), determining that the first data set is not corrupted (104). The method (100) also comprises in parallel to the uploading performing selecting from the first data set a predefined number of records and building a second data set (106), determining statistical data and metadata about the first data set (108), and visualizing the second data set, the statistical data and the metadata (110).

Scenario identification for validation and training of machine learning based models for autonomous vehicles

A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.

Способ достоверного прослеживания истории владения объектами

Изобретение относится к области вычислительной техники для проверки подлинности и достоверного прослеживания истории владения индивидуально-определёнными текстильными изделиями. Технический результат заключается в расширении арсенала технических средств проверки подлинности объекта. Технический результат достигается за счет того, что в программное обеспечение вносится и предоставляется при проверке в том числе информация о первоначальном владельце индивидуально-определённого текстильного изделия, о всех или некоторых последующих владельцах индивидуально-определённого текстильного изделия, в данном способе каждому владельцу индивидуально-определённого текстильного изделия предоставляется право на внесение информации о себе в цепочку владельцев или сохранение анонимности, фотография метки, вносимая в программное обеспечение при регистрации индивидуально-определённого текстильного изделия, преобразуется в невзаимозаменяемый токен, при этом метка имеет либо естественное происхождение и представляет ...

Systems and methods for creating machine vision jobs including barcode scanning

A method for creating one or more machine vision jobs that include barcode scanning. One or more processors detect a first configuration of a barcode scanning tool, including its settings. When a first imaging device is operated in a fixed scanning mode using the configuration 308, the device scans a barcode. The first configuration is modified to a second configuration which causes a second imaging device to operate in a machine vision mode in accordance with the second configuration. A graphical user interface 300 displays a user-selectable option to add the barcode scanning tool configured to the second configuration to a machine vision job 314. The two imaging devices may be the same camera. The user may select options to add the barcode scanning tool to a machine vision job, which are displayed by the GUI. The user may also select other machine vision tools such as binarization, pattern matching, or edge detection tools. A computer system for carrying out the method is also claimed ...

SYSTEM AND METHOD FOR FINDING AND CLASSIFYING LINES IN AN IMAGE WITH A VISION SYSTEM

This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.

Image collection and labelling using computer system and analysis

A method, a computing system and a computer program product for collecting and labelling images includes capturing a video of an object with a camera. A movement trace of a pointer is recorded that outlines the object while capturing the video of the object. Further included is generating a labeled image based at least on the captured video of the object and the recorded movement trace of the pointer. The labeled image includes the object and a line that surrounds the object.

Automated digital tool identification from a rasterized image

A system identifies, automatically and without user intervention, digital tool parameters for achieving a visual appearance of an image region in raster image data. The system processes raster image data using a tool detection module 202 to identify the tool and a parameter estimation module 216 determines tool parameters for controlling the tool to achieve the visual appearance. The system generates an image tool description 110 based on the tool and the parameter configuration and incorporates the image tool description into the raster image data to create an interactive image 120 which indicates a region of the image having a visual appearance achievable using the tool. The tool detection and parameter estimation steps may be carried out by trained neural networks. The image tool description may enable transfer of the digital tool parameter configuration to different image data. Also claimed is a corresponding method and a system for generating training data used in training neural networks ...

SYSTEM, DEVICE AND METHOD FOR OBJECT DETECTION IN VIDEO FEEDS

Embodiments are directed to a smart camera device that analyzes independent video streams.

Generating data in a messaging system for a machine learning model

Systems and methods are provided for analyzing, by a computing device, location data associated with a location of the computing device to determine that an image or video captured using a messaging application on the computing device is captured near a food-related venue or event, receiving input related to food associated with the food-related venue or event, sending the image or video and the input related to food associated with the food-related venue or event to a computing system to train a machine learning model for food detection, and updating the messaging application to comprise the trained machine learning model for food detection.

Example-based image annotation

Techniques are generally described for machine learning exampled-based annotation of image data. In some examples, a first machine learning model may receive a query image comprising a first depiction of an object-of-interest. In some examples, the first machine learning model may receive a target image representing a scene in which a second depiction of the object-of-interest is visually represented. In various examples, the first machine learning model may generate annotated output image data that identifies a location of the second depiction of the object-of-interest within the target image. In some examples, an object detection model may be trained based at least in part on the annotated output image data.

Retraining a computer vision model for robotic process automation

A Computer Vision (CV) model generated by a Machine Learning (ML) system may be retrained for more accurate computer image analysis in Robotic Process Automation (RPA). A designer application may receive a selection of a misidentified or non-identified graphical component in an image form a user, determine representative data of an area of the image that includes the selection, and transmit the representative data and the image to an image database. A reviewer may execute the CV model, or cause the CV model to be executed, to confirm that the error exists, and if so, send the image and a correct label to an ML system for retraining. While the CV model is being retrained, an alternative image recognition model may be used to identify the misidentified or non-identified graphical component.

Personalized automated machine learning

A method is provided for personalizing machine learning models for users of an automated machine learning system, the machine learning models being generated by an automated machine learning system. The method includes obtaining a first set of datasets for training first, second, and third neural networks, inputting the training datasets to the neural networks, tuning hyperparameters for the first, second, and third neural networks for testing and training the neural networks, inputting a second set of datasets to the trained neural networks and the third neural network generating a third output data including a relevance score for each of the users for each of the machine learning models, and displaying a list of machine learning models associated with each of the users, with each of the machine learning models showing the relevance score.

Systems and methods for creating machine vision jobs including barcode scanning

VIDEO SURVEILLANCE SYSTEM, VIDEO PROCESSING APPARATUS, VIDEO PROCESSING METHOD, AND VIDEO PROCESSING PROGRAM

A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.

Image processing apparatus and control method therefor, image capturing apparatus, and storage medium

An apparatus comprises a storage device configured to store a plurality of dictionary data for respectively detecting a plurality of different objects from an image; and at least one processor configured to function as: a detection unit configured to use partial dictionary data of the plurality of dictionary data to detect an object corresponding to the partial dictionary data, with respect to each frame of an image of a plurality of frames obtained by an image capturing device; and a switching unit configured to switch the dictionary data to be used by the detection unit in the plurality of frames, according to a result of the object detection by the detection unit.

Cloud-based framework for processing, analyzing, and visualizing imaging data

Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for detecting objects located in an area of interest. In accordance with one embodiment, a method is provided comprising: receiving, via an interface provided through a general instance on a cloud environment, imaging data comprising raw images collected on the area of interest; upon receiving the images: activating a central processing unit (CPU) focused instance on the cloud environment and processing, via the image, the raw images to generate an image map of the area of interest; and after generating the image map: activating a graphical processing unit (GPU) focused instance on the cloud environment and performing object detection, via the image, on a region within the image map by applying one or more object detection algorithms to the region to identify locations of the objects in the region.

Video surveillance system, video processing apparatus, video processing method, and video processing program

A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.

Image processing system, image processing method, and storage medium

To reduce the possibility of false determination for a character string alteration in image data, embodiments of the present disclosure include a generation unit configured to generate a learning model by performing machine learning processing based on an altered character image, a character image before an alteration, and an image representing the difference between the altered character image and the character image before the alteration, an input unit configured to input image data, and an estimation unit configured to estimate whether the image data input by the input unit includes an altered character, by using the learning model generated by the generation unit.

COMPUTING SYSTEM FOR EXTRACTION OF TEXTUAL ELEMENTS FROM A DOCUMENT

Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

IDENTIFICATION OF EFFECT PIGMENTS IN A TARGET COATING

REAL-TIME SYNTHETICALLY GENERATED VIDEO FROM STILL FRAMES

Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized ...

Methods and apparatus to add common sense reasoning to artificial intelligence in the context of human machine interfaces

Methods, apparatus, systems and articles of manufacture are disclosed to add common sense to a human machine interface. Disclosed examples include a human machine interface system that having an actuator to cause artificial intelligence to execute in a virtual execution environment to generate a virtual response to a user input. The system also includes a virtual consequence evaluator to evaluate a virtual consequence that follows from the virtual response, the virtual consequence generated by executing a model of human interactions, and an output device controller to cause an output device to perform a non-virtual response to the user input when the virtual consequence evaluator evaluates the virtual consequence as positive.

Creating data shapes for pattern recognition systems

Methods, apparatuses and systems directed to pattern identification and pattern recognition. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In some implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes.

Systems And Methods For Classification Of Arterial Image Regions And Features Thereof

In part, the disclosure relates to methods, and systems suitable for evaluating image data from a patient on a real time or substantially real time basis using machine learning (ML) methods and systems. Systems and methods for improving diagnostic tools for end users such as cardiologists and imaging specialists using machine learning techniques applied to specific problems associated with intravascular images that have polar representations. Further, given the use of rotating probes to obtain image data for OCT, IVUS, and other imaging data, dealing with the two coordinate systems associated therewith creates challenges. The present disclosure addresses these and numerous other challenges relating to solving the problem of quickly imaging and diagnosis a patient such that stenting and other procedures may be applied during a single session in the cath lab.

Real-time synthetically generated video from still frames

Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized ...

System and method for image-based crop identification

A system and a method for image-based crop identification are disclosed. The image-based crop identification system includes a database, a communication module and a model library. The database stores sample aerial data and annotated aerial data. The communication module is coupled to the database, and is configured to provide the sample aerial data to a user and receive the annotated aerial data from the user. The model library is coupled to the database, and is configured to obtain the annotated aerial data, train a crop classification model based on the annotated aerial data, and provide the trained crop classification model for subsequent crop identification. The annotated aerial data include determination of the type of the crop appearing in the sample aerial data.

Advanced loop selection systems and methods for supporting efficient echo comparison

A system and method for selecting image sequences of echocardiogram studies for visual comparison by a user. The method includes receiving image sequences from a current study and a prior study to be compared. The method includes determining a relevant view of the image sequences of the current and prior studies and selecting an image sequence from one of the current and prior studies to a user via an interactive comparison panel. The method includes determining which image sequence of the relevant view of an other of the current and prior studies that most closely matches the selected image sequence via the interactive comparison panel.

Electronic device for reconstructing an artificial intelligence model and a control method thereof

An electronic device for reconstructing an artificial intelligence model, and a control method thereof are provided. The control method includes inputting at least one input data to a first artificial intelligence (AI) model, to acquire at least one output data, acquiring first usage information, based on the acquired at least one output data, acquiring first reconstruction information for reconstructing the first AI model, based on the acquired first usage information, and reconstructing the first AI model, based on the acquired first reconstruction information, to acquire a second AI model.

Data retrieval in pattern recognition systems

Methods, apparatuses and systems directed to pattern identification and pattern recognition. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In some implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes.

Reconfigurable parallel 3-dimensional convolution cluster engine

Disclosed is a reconfigurable parallel 3-Dimensional (3-D) convolution engine for performing 3-D Convolution and parallel feature map extraction on an image. The reconfigurable parallel 3-D convolution engine further comprises a plurality of CNN reconfigurable engines configured to perform 3-D convolution, in parallel, to process a plurality of feature maps, a kernel memory space, present in each instance of CNN reconfigurable engine, capable for holding a set of parameters associated to a network layer having each operational instance of CNN reconfigurable engine, and at least one memory controller, an Input Feature Map Memory (FMM) cluster and an Output FMM cluster.

Text-to-visual machine learning embedding techniques

Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

SYSTEMS AND METHODS FOR SYNTHETIC DATA GENERATION FOR TIME-SERIES DATA USING DATA SEGMENTS

Systems and methods for generating synthetic 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 a dataset including time-series data. The operations may include generating a plurality of data segments based on the dataset, determining respective segment parameters of the data segments, and determining respective distribution measures of the data segments. The operations may include training a parameter model to generate synthetic segment parameters. Training the parameter model may be based on the segment parameters. The operations may include training a distribution model to generate synthetic data segments. Training the distribution model may be based on the distribution measures and the segment parameters. The operations may include generating a synthetic dataset using the parameter model and the distribution model ...

Method for monitoring manufacture of assembly units

One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units ...

Machine learning to generate and evaluate visualizations

Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for machine learning to generate and evaluate visualizations. In some implementations, a system determines properties of a dataset. The system generates visualization specifications that each define a different visualization for the dataset, wherein the visualization specifications specify different subsets of the dataset being illustrated with different visualization formats. The system evaluates the visualization specifications using a machine learning model trained based on user feedback for visualizations for multiple datasets. The system selects a subset of the visualization specifications based on output of the machine learning model. The system provides, for display, visualization data for the subset of visualization specifications that were selected based on the output of the machine learning model.

Home UI system for managing digital ink

A home user interface (UI) system for managing digital ink is provided. The home UI system includes a plurality of state sensors capable of detecting a state in a house or a change in the state, and a plurality of home-use devices that are provided in the house or that form part of the house and that each include a handwriting sensor capable of detecting handwriting made by a person. The home UI system further includes one or more notification units that are configured to notify the person of the existence of the home-use device or a detectable region of the handwriting sensor of the home-use device. The home UI system further includes a controller which, when it is determined that a notification is necessary from a detection result of one or more of the state sensors, instructs at least one of the notification units to carry out the notification.

Method and system of controlling device using real-time indoor image

A device and a method for controlling a device using a real-time image are provided. The method includes: receiving an image captured by an image capturing device connected to a network to display the image in real-time; searching for the device that is connected to the network and is controllable; designating, within the image, a setting zone corresponding to the device; receiving a user input; and controlling the device selected according to the user input. A location of the setting zone within the image may be updated according to a change in the image. The user may receive immediate visual feedback on how the devices are being controlled. The user may control a device displayed on the screen on which the real-time indoor image is displayed without having to navigate through different sub-menus for different devices.

Interactive iterative image annotation

A system and computer-implemented method are provided for annotation of image data. A user is enabled to iteratively annotate the image data. An iteration of said iterative annotation comprises generating labels for a current image data part based on user-verified labels of a previous image data part, and enabling the user to verify and correct said generated labels to obtain user-verified labels for the current image data part. The labels for the current image data part are generated by combining respective outputs of a label propagation algorithm and a machine-learned classifier trained on user-verified labels and image data and applied to image data of the current image data part. The machine-learned classifier is retrained using the user-verified labels and the image data of the current image data part to obtain a retrained machine-learned classifier.

Systems and methods for training image processing models for vehicle data collection

Systems and methods for training image processing models for vehicle data collection by image analysis are provided. An example method involves accessing an image of a field of interest in a vehicle captured by a camera in the vehicle, providing a user interface to, display the image, receive input that defines a region of interest in the image that is expected to convey vehicle information, and receive input that assigns a label to the region of interest that associates the region of interest with an image processing model that is to be trained to extract a type of vehicle information from the region of interest, and contributing the image, labelled with the region of interest and the label associating the region of interest to the image processing model, to a training data library to train the image processing model.

CLOUD-BASED FRAMEWORK FOR PROCESSING, ANALYZING, AND VISUALIZING IMAGING DATA

Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for detecting objects located in an area of interest. In accordance with one embodiment, a method is provided comprising: receiving, via an interface provided through a general instance on a cloud environment, imaging data comprising raw images collected on the area of interest; upon receiving the images: activating a central processing unit (CPU) focused instance on the cloud environment and processing, via the image, the raw images to generate an image map of the area of interest; and after generating the image map: activating a graphical processing unit (GPU) focused instance on the cloud environment and performing object detection, via the image, on a region within the image map by applying one or more object detection algorithms to the region to identify locations of the objects in the region.

MICROORGANIC DETECTION SYSTEM WITH WORKLISTS

GENERATING DATA IN A MESSAGING SYSTEM FOR A MACHINE LEARNING MODEL

Systems and methods are provided for analyzing, by a computing device, location data associated with a location of the computing device to determine that an image or video captured using a messaging application on the computing device is captured near a food-related venue or event, receiving input related to food associated with the food-related venue or event, sending the image or video and the input related to food associated with the food-related venue or event to a computing system to train a machine learning model for food detection, and updating the messaging application to comprise the trained machine learning model for food detection.

Laser gas detector and laser gas detection system

A laser gas detection system includes a laser gas detector and a near-eye display device. The laser gas detection system provided in the present disclosure incorporates modern display technologies and modern communication facilities to present detection results to a user of the laser gas detection system in various intuitive and highly readable forms. The laser gas detection system is further capable of projecting the detection results to a field of view of the user through the near-eye display device.

CONTEXT-AWARE EVENT BASED ANNOTATION SYSTEM FOR MEDIA ASSET

Various embodiments described herein support or provide for annotation of a media asset, such as an audio asset or a video asset, based on one or more events identified within content of the media asset. In particular, some embodiments can determine one or more of the following details with respect to content of a given media asset, which can represent annotations that enable determination of contextual information for the given media asset: events; event classification labels for events; subclassifications labels for events; scenes comprising events; attributes of scenes; themes presented by the content; and title-level attributes of the given media asset.

Systems And Methods For Classification Of Arterial Image Regions And Features Thereof

In part, the disclosure relates to methods, and systems suitable for evaluating image data from a patient on a real time or substantially real time basis using machine learning (ML) methods and systems. Systems and methods for improving diagnostic tools for end users such as cardiologists and imaging specialists using machine learning techniques applied to specific problems associated with intravascular images that have polar representations. Further, given the use of rotating probes to obtain image data for OCT, IVUS, and other imaging data, dealing with the two coordinate systems associated therewith creates challenges. The present disclosure addresses these and numerous other challenges relating to solving the problem of quickly imaging and diagnosis a patient such that stenting and other procedures may be applied during a single session in the cath lab.

Systems And Methods For Classification Of Arterial Image Regions And Features Thereof

In part, the disclosure relates to methods, and systems suitable for evaluating image data from a patient on a real time or substantially real time basis using machine learning (ML) methods and systems. Systems and methods for improving diagnostic tools for end users such as cardiologists and imaging specialists using machine learning techniques applied to specific problems associated with intravascular images that have polar representations. Further, given the use of rotating probes to obtain image data for OCT, IVUS, and other imaging data, dealing with the two coordinate systems associated therewith creates challenges. The present disclosure addresses these and numerous other challenges relating to solving the problem of quickly imaging and diagnosis a patient such that stenting and other procedures may be applied during a single session in the cath lab.

Machine learning driven rules engine for dynamic data-driven enterprise application

The present invention generally relates to system, method and graphical user interface for executing one or more tasks in dynamic data driven enterprise application. The invention includes creation of rules on a rule creation interface by one or more syntax from a rule creation syntax data library. The invention provides machine learning models driven rule engine for executing the tasks.

METHOD FOR MONITORING MANUFACTURE OF ASSEMBLY UNITS

One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units ...

Medical information processing apparatus, medical information processing method, and non-transitory computer-readable storage medium

A medical information processing apparatus comprises an obtaining unit that obtains medical information, a learning unit that performs learning on a function of the medical information processing apparatus using the medical information, an evaluation data holding unit that holds evaluation data in which a correct answer to be obtained by executing the function is known, the evaluation data being for evaluating a learning result of the learning unit, an evaluating unit that evaluates a learning result obtained through learning, based on the evaluation data, and an accepting unit that accepts an instruction to apply a learning result of the learning unit to the function.

Responding to machine learning requests from multiple clients

A method includes receiving, with a computing device, a first client request from a first client that identifies a machine learning model and a sensor. The method includes sending, with the computing device, a call to a server to apply the identified machine learning model to a set of data from the identified sensor, in response to the first client request. The method includes receiving, with the computing device, a second client request from a second client that identifies a same machine learning model and sensor as the first client request. The method includes sending, with the computing device, response data from the identified machine learning model to both the first client and the second client without sending an additional call to the server in response to the second client request.

Semi-automated system and method for assessment of responses

Embodiments of the invention provide a semi-automated system and method for assessment of student work product. The method may comprise obtaining a plurality of student work product from a plurality of students, identifying motifs present in the student work product, forming a subset of motifs, clustering the work product into clusters based on the subset of motifs, receiving an assessment from a teacher relevant to clusters and providing assessment for a work product based on the cluster assessment. Methods according to embodiments of the invention may reduce teachers' review and feedback time and increase consistency and quality of feedback given to students.

Data model generation using generative adversarial networks

Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

AI capability research and development platform and data processing method

Embodiments of the present disclosure provide an AI capability research and development platform and a data processing method. The AI capability research and development platform includes: a data management module, a tool management module, a process management module and a model management module, where the data management module is configured to perform data processing on received data, including at least one of the following: analyzing data type of the data, converting the data according to preset data format and storing the data; the tool management module is configured to store at least one tool, each tool being used to execute a preset processing flow; the process management module is configured to perform model training according to the tool provided by the tool management module and the data provided by the data management module; the model management module is configured to store a model obtained by the model training.

Machine learning model creation via user-configured model building blocks

Techniques for machine learning (ML) model training and deployment using model building blocks via graphical user interfaces (GUIs) are described. Users can use a GUI provided by an electronic device to select and configure ML aspects for one or more ML models to be trained using identified training data. The electronic device can send a request to cause a model construction service to train one or more ML models based on the user configuration, return results of the training to the user within the GUI, and deploy one or more of the ML models.

METHOD AND SYSTEM FOR INITIATING AN ACTION IN A UTILITY SYSTEM, INDUSTRIAL SYSTEM, OR COMMUNICATION NETWORK

Attribute control techniques for image editing

Systems and methods dynamically adjust an available range for editing an attribute in an image. An image editing system computes a metric for an attribute in an input image as a function of a latent space representation of the input image and a filtering vector for editing the input image. The image editing system compares the metric to a threshold. If the metric exceeds the threshold, then the image editing system selects a first range for editing the attribute in the input image. If the metric does not exceed the threshold, a second range is selected. The image editing system causes display of a user interface for editing the input image comprising an interface element for editing the attribute within the selected range.

Systems and user interfaces for dynamic and interactive investigation of bad actor behavior based on automatic clustering of related data in various data structures

Embodiments of the present disclosure relate to a data analysis system that may automatically generate memory-efficient clustered data structures, automatically analyze those clustered data structures, automatically tag and group those clustered data structures, and provide results of the automated analysis and grouping in an optimized way to an analyst. The automated analysis of the clustered data structures (also referred to herein as data clusters) may include an automated application of various criteria or rules so as to generate a tiled display of the groups of related data clusters such that the analyst may quickly and efficiently evaluate the groups of data clusters. In particular, the groups of data clusters may be dynamically re-grouped and/or filtered in an interactive user interface so as to enable an analyst to quickly navigate among information associated with various groups of data clusters and efficiently evaluate those data clusters in the context of, for example, a fraud ...

System and method for job profile matching

A computer-implemented system for job matching of candidates and vacancies, comprises: a candidate memory storing data of at least one candidate profile associated with a respective candidate and consisting of a plurality of different candidate categories, wherein each candidate category comprises candidate category data associated with the candidate; and a vacancy memory storing data of at least one vacancy profile associated with a respective vacancy and consisting of a plurality of different vacancy categories, wherein each vacancy category comprises vacancy category data associated with the vacancy. A matching module is configured to receive the at least one candidate profile, receive the at least one vacancy profile, determine at least one similarity score between the at least one candidate profile and the at least one vacancy profile, and determine a job matching result based on the at least one similarity score. An information module is configured to communicate the job matching ...

Automated analytical model retraining with a knowledge graph

A model retraining tool is provided for utilizing a knowledge graph to retrain analytical models used in production. The model retraining tool retrains the analytical models to improve performance of the analytical models in an efficient and resource conserving manner.

DATA MODEL GENERATION USING GENERATIVE ADVERSARIAL NETWORKS

Methods for generating data models using a generative adversarial network can begin by receiving a data model generation request by a model optimizer from an interface. The model optimizer can provision computing resources with a data model. As a further step, a synthetic dataset for training the data model can be generated using a generative network of a generative adversarial network, the generative network trained to generate output data differing at least a predetermined amount from a reference dataset according to a similarity metric. The computing resources can train the data model using the synthetic dataset. The model optimizer can evaluate performance criteria of the data model and, based on the evaluation of the performance criteria of the data model, store the data model and metadata of the data model in a model storage. The data model can then be used to process production data.

SYSTEMS AND METHODS FOR SYNTHETIC DATA GENERATION

A cloud computing system can be configured to generate data models. A model optimizer of the cloud computing system can provision computing resources of the cloud computing system with a data model. A dataset generator of the cloud computing system can generate a synthetic dataset for training the data model. The computing resources can train the data model using the synthetic dataset. The model optimizer can store the data model and metadata of the data model in a model storage. The cloud computing system can receive production data from a data source by a production instance of the cloud computing system using a common file system. The production data can be processed using the data model by the production instance. The computing resources, the dataset generator, and the model optimizer can be hosted by separate virtual computing instances of the cloud computing system.

Document digitization, transformation and validation

An Artificial Intelligence (AI) based document digitization, transformation and validation system extracts fields from digital documents via different document digitization processes. A document packet with a plurality of documents is initially accessed and any non-digital documents in the document packet are digitized. The errors in the digitized documents are corrected and non-English documents are translated into English. Each of the documents is provided to a plurality of digitization services for the extraction of fields by a plurality of field extraction models. If a field has multiple field instances extracted by more than one digitization service, then a field instance with the highest confidence score is selected for inclusion into the consolidated results. The consolidated results produced in different JavaScript Object Notation (JSON) formats are converted into a common JSON format which may be further validated and provided to downstream processes.

Machine learning model development with interactive feature construction and selection

Subject matter described herein includes generating a visual environment for interactive development of a machine learning (ML) model. The method includes accessing observations of data each of which includes values of independent variables and a dependent variable. The method includes performing an interactive feature construction and selection in which select independent variables are selected as or transformed into a set of features for use in building a ML model to predict the dependent variable. The method includes building the ML model using a ML algorithm, the set of features, and a training set produced from the set of features and observations of the data. And the method includes outputting the ML model for deployment to predict the dependent variable for additional observations of the data.

OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDIUM

Provided is an object detection device for efficiently and simply selecting an image for creating instructor data on the basis of the number of detected objects. The object detection device is provided with: a detection unit for detecting an object from each of a plurality of input images using a dictionary; an acceptance unit for displaying, on a display device, a graph indicating the relationship between the input images and the number of subregions in which the objects are detected, and displaying, on the display device, in order to create instructor data, one input image among the plurality of input images in accordance with a position on the graph accepted by operation of an input device; a generation unit for generating the instructor data from the input image; and a learning unit for learning a dictionary from the instructor data.

Some automated and semi-automated tools for linear feature extraction in two and three dimensions

A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.

TECHNOLOGY FOR BUILDING AND MANAGING DATA MODELS

Techniques for building and managing data models are provided. According to certain aspects, systems and methods may enable a user to input parameters associated with building one or more data models, including parameters associated with sampling, binning, and other factors. The systems and methods may automatically generate program code that corresponds to the inputted parameters and display the program code for review by the user. The systems and methods may build the data models and generate charts and plots depicting aspects of the data models. Additionally, the systems and methods may combine data models and select champion data models.

System and method for finding and classifying lines in an image with a vision system

This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.

System and method of generating bounding polygons

An example system includes a first and second digital device. The first digital device may be configured to provide an interface displaying an image including a depiction of an object, place a bounding shape around the object, and crop contents of the bounding shape to create a portion. The second digital device may be configured to receive the portion, retrieve high-level features and low-level features, apply first Atrous Spatial Pyramid Pooling (ASPP) to the high-level features to aggregate the high-level features as aggregate features, concatenate results to create the aggregate features, up-sample, apply a convolution to the low-level features, concatenate the aggregate features with the low-level features after convolution to form combined features, segment the combined features to generate a polygonal shape outline along outer boundaries of the first object, and provide the first polygonal shape outline to the first digital device for display.

Knowledge engine module collections

Certain aspects of the present disclose provide techniques for generating a knowledge engine module collection. Techniques for generating the module collection include receiving input data comprising a first identifier, a second identifier, and a third set of fields. Based on the input data, a UI builder tool can retrieve a first set of artifact files and a second set of artifact files corresponding to a first module and a second module. The UI builder tool can generate a third set of artifact files based on the first set of artifact files, the second set of artifact files, and the input data.

Pattern recognition systems

Methods, apparatuses and systems directed to pattern identification and pattern recognition. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In some implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes.

Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges

Lifelong Deep Neural Network (L-DNN) technology revolutionizes Deep Learning by enabling fast, post-deployment learning without extensive training, heavy computing resources, or massive data storage. It uses a representation-rich, DNN-based subsystem (Module A) with a fast-learning subsystem (Module B) to learn new features quickly without forgetting previously learned features. Compared to a conventional DNN, L-DNN uses much less data to build robust networks, dramatically shorter training time, and learning on-device instead of on servers. It can add new knowledge without re-training or storing data. As a result, an edge device with L-DNN can learn continuously after deployment, eliminating massive costs in data collection and annotation, memory and data storage, and compute power. This fast, local, on-device learning can be used for security, supply chain monitoring, disaster and emergency response, and drone-based inspection of infrastructure and properties, among other applications ...

METHOD AND APPARATUS FOR DETECTING FACE ATTRIBUTE, STORAGE MEDIUM AND ELECTRONIC DEVICE

A method and apparatus for detecting a face attribute, a computer-readable storage medium and an electronic device are provided. The method includes: extracting a face image from a candidate image; acquiring a target image block corresponding to at least one target part of the face image; and obtaining, for one of the at least one target part, target attribute information by performing attribute detection on the target image block corresponding to the target part using a pre-trained attribute detection model corresponding to the target part.

MOBILE DEVICE PLATFORM FOR AUTOMATED VISUAL RETAIL PRODUCT RECOGNITION

A computer-implemented method for configuring a mobile point-of-sale application to perform automated product-recognition checkout processes. The application includes a convolutional neural network including hidden layer n positioned downstream of remaining hidden layers and downstream of an input segment of the convolutional neural network. The method includes: appending a fine classification arm operating on output from hidden layer n and having a first loss function for generating output; appending a second classification arm operating on the output from one of the remaining n hidden layers upstream from hidden layer n and having a second loss function for generating output; providing a plurality of true labels for image subset(s) and applicable to at least one product class; and training the CNN by passing the image subsets therethrough, observing corresponding output of the first and second loss functions, and iteratively adjusting values of CNN model parameters based on the loss function ...

Segmentation using an unsupervised neural network training technique

Systems and methods to detect one or more segments of one or more objects within one or more images based, at least in part, on a neural network trained in an unsupervised manner to infer the one or more segments. Systems and methods to help train one or more neural networks to detect one or more segments of one or more objects within one or more images in an unsupervised manner.

COMPUTER-IMPLEMENTED, ADAPTED ANOMALY DETECTION METHOD FOR POWDER-BED-BASED ADDITIVE MANUFACTURING

Computing system for extraction of textual elements from a document

Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text within a two-dimensional area represented by the document. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

Automated document highlighting in a digital management platform

A highlighting engine modifies a target document by identifying and highlighting a set of text passages. The highlighting engine receives a training set of data including documents that each include a set of highlighted text passages. The highlighting engine trains a machine learned model using the training set of data. The trained machine learned model, when applied to subsequent identified candidate sets of text passages within the target document, identifies the set of text passages to highlight. The highlighting engine modifies the target document with the highlighted set of text passages and provides the modified target document for display via an interface. The highlighted set of text passages enable a user to quickly read and understand the target document.

UTILIZING INTERACTIVE DEEP LEARNING TO SELECT OBJECTS IN DIGITAL VISUAL MEDIA

Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Automated digital tool identification from a rasterized image

A visual lens system is described that identifies, automatically and without user intervention, digital tool parameters for achieving a visual appearance of an image region in raster image data. To do so, the visual lens system processes raster image data using a tool region detection network trained to output a mask indicating whether the digital tool is useable to achieve a visual appearance of each pixel in the raster image data. The mask is then processed by a tool parameter estimation network trained to generate a probability distribution indicating an estimation of discrete parameter configurations applicable to the digital tool to achieve the visual appearance. The visual lens system generates an image tool description for the parameter configuration and incorporates the image tool description into an interactive image for the raster image data. The image tool description enables transfer of the digital tool parameter configuration to different image data.

Creating synthetic visual inspection data sets using augmented reality

In an approach for creating synthetic visual inspection data sets for training an artificial intelligence computer vision deep learning model utilizing augmented reality, a processor enables a user to capture a plurality of images of an anchor object using a camera on a user computing device. A processor receives the plurality of images of the anchor object from the user. A processor generates a baseline model of an anchor object. A processor generates a training data set. A processor trains the baseline model of the anchor object. A processor creates a trained Artificial Intelligence (AI) computer vision deep learning model. A processor enables the user to interact with the trained AI computer vision deep learning model in an access mode.

Methods and systems for programmatic creation of an interactive demonstration presentation for an envisioned software product

A demonstration serving system and associated methods are provided for creating an interactive demonstration presentation for an envisioned software product. The interactive demonstration presentation for the envisioned software product is a digital artifact that is presented during a presentation to present and demonstrate features of the envisioned software product and how the envisioned software product is to function and operate in response to user interaction with a graphical user interface (GUI) such that the interactive demonstration presentation mimics features, look, and feel of the envisioned software product once it is fully developed without creating custom-made Hypertext Markup Language (HTML), JavaScript and Cascading Style Sheets (CSS) of a real software product.

Laser gas detector and laser gas detection system

A laser gas detection system includes a laser gas detector and a near-eye display device. The laser gas detection system provided in the present disclosure incorporates modern display technologies and modern communication facilities to present detection results to a user of the laser gas detection system in various intuitive and highly readable forms. The laser gas detection system is further capable of projecting the detection results to a field of view of the user through the near-eye display device.

Technology for building and managing data models

Techniques for building and managing data models are provided. According to certain aspects, systems and methods may enable a user to input parameters associated with building one or more data models, including parameters associated with sampling, binning, and other factors. The systems and methods may automatically generate program code that corresponds to the inputted parameters and display the program code for review by the user. The systems and methods may build the data models and generate charts and plots depicting aspects of the data models. Additionally, the systems and methods may combine data models and select champion data models.

System, device and method for object detection in video feeds

Embodiments are directed to a smart camera device that analyzes independent video streams.

Method and system for image search

A method and system for image search, the method comprising: receiving an indication regarding at least one feature of at least one image from a collection of images; creating an updated search algorithm according to the indication; and providing an updated collection of images by using the updated search algorithm.

Methods and apparatus for retrieving images from a large collection of images

A processing system may receive an example image for use in querying a collection of digital images. The processing system may use local and global feature descriptors to perform a content-based image comparison of the digital images with the example image, to automatically rank the digital images with respect to similarity to the example image. A local feature descriptor may represent a portion of the contents of a digital image. A global feature descriptor may represent substantially all of the contents of that digital image. The global feature descriptor may be content based, not keyword based. Intermediate and final classifiers may be used to perform the automatic ranking. Different intermediate classifiers may generate intermediate relevance metrics with respect to different modalities. The final classifier may use results from the intermediate classifiers to produce a final relevance metric for the digital images. Other embodiments are described and claimed.

Methods and apparatus related to gate boundaries within a data space

In one embodiment, one or more processor-readable media storing code representing instructions that when executed by one or more processors cause the one or more processors to receive a set of parameter values defining a boundary within a data space associated with a dataset. The dataset can represent signaling related to a test substance. A first metric can be defined based on a first portion of the dataset associated with a first region defined by the boundary. A second metric can be defined based on a second portion of the dataset associated with a second region defined by the boundary after the boundary is modified. The second region can be different than the first region.

Empirical data modeling

Methods, apparatuses and systems directed to pattern identification and pattern recognition. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In some implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multi-level pattern recognition schemes.

Electronic apparatus and image display method

According to one embodiment, an electronic apparatus includes a viewer image generating module, a viewer recognition module, a group extraction module, and an image display module. The viewer image generating module generates an image of a viewer by capturing the image of the viewer. The viewer recognition module detects a face image in the generated image and recognizes the viewer corresponding to the detected face image. The group extraction module extracts, from a plurality of groups each including still images, groups including at least one of a still image including the face image of the viewer and a still image imported by the viewer. The image display module displays still images in the extracted groups on a screen.

Image processing system providing selective arrangement and configuration for an image analysis sequence

A computer-implemented method of processing a selected image using multiple processing operations is provided. An image analysis sequence having multiple processing steps is constructed. The image analysis sequence is constructed in response to receipt of multiple processing operation selections. Individual processing steps in the image analysis sequence are associated with a processing operation that is indicated in a corresponding processing operation selection. The processing steps are arranged in response to receipt of arrangement information that relates to a selective arrangement of the processing steps. At least one of the processing steps in the image analysis sequence is configured such that the processing operation associated with the processing step processes a specified input image to generate an output image when the processing step is performed. A display signal is generated for display of the output image at a display device.

Image analysis

A first aspect of the invention relates to an apparatus 100 for genotoxicological screening. The apparatus 100 comprises a processor 114 for analysing images. The processor 114 is configured to provide an identifier module 115 for identifying target cells in an image and a dynamically modifiable classifier module 116 for classifying the identified cells in accordance with one or more phenotype, such as micronuclei, for example. The processor 114 is also configured to provide a scoring module 117 for assigning respective confidence measurements to the classified cells. Various aspects and embodiments of the invention may be used, for example, to provide for improved reliability and accuracy when performing automated high-throughput screening (HTS) drug assays.

Interactive and automated tissue image analysis with global training database and variable-abstraction processing in cytological specimen classification and laser capture microdissection applications

A system and method for performing tissue image analysis and region of interest identification for further processing applications such as laser capture microdissection is provided. The invention provides three-stage processing with flexible state transition that allows image recognition to be performed at an appropriate level of abstraction. The three stages include processing at one or more than one of the pixel, subimage and object levels of processing. Also, the invention provides both an interactive mode and a high-throughput batch mode which employs training files generated automatically.

Image-monitoring device and method for ssearching for objects therefor

Disclosed are an image monitoring device capable of searching an object on the basis of a statistical model with respect to the characteristics of an object detected from a monitored image to thereby provide an object search function resistant to a variation in the characteristics of an object according to a monitoring environment, and a method for searching an object thereof. The method for searching an object by an image monitoring device, including: displaying a characteristic value of an object detected from a monitored image and a detection frequency of an object having the characteristic value on a first region; searching a frame, in which an object having a characteristic value selected from characteristic values displayed on the first region is detected, from the monitored image; and displaying the searched frame in a second region.

Systems and methods for performing quality review scoring of biomarkers and image analysis methods for biological tissue

Exemplary embodiments include methods, systems, and devices for enabling users to provide quality scores for indicating the quality of image analysis methods performed on images of biological tissue. An exemplary user interface displays results of an image analysis method performed on an image of biological tissue in an overlaid manner on an image of biological tissue. The exemplary user interface enable a user to provide, directly on the user interface, one or more quality scores to indicate the user's assessment of the quality of the image analysis performed on the image. Exemplary embodiments store the quality scores provided by the user in association with the image analysis method and the image of biological tissue.

Image processing architectures and methods

Cell phones and other portable devices are equipped with a variety of technologies by which existing functionality is improved, and new functionality is provided. Some aspects relate to imaging architectures, in which a cell phone's image sensor is one in a chain of stages that successively act on instructions/data, to capture and later process imagery. Other aspects relate to distribution of processing tasks between the device and remote resources (“the cloud”). Elemental image processing, such as filtering and edge detection—and even some simpler template matching operations—may be performed on the cell phone. Other operations are referred out to remote service providers. The remote service providers can be identified using techniques such as a reverse auction, though which they compete for processing tasks. Other aspects of the disclosed technologies relate to visual search capabilities, and determining appropriate actions responsive to different image inputs. Still others concern metadata generation, processing, and representation. A great number of other features and arrangements are also detailed.

Detecting facial similarity based on human perception of facial similarity

Similar faces may be determined within images based on human perception of facial similarity. The user may provide an image including a query face to which the user wishes to find faces that are similar. Similar faces may be determined based on similarity information. Similarity information may be generated from information related to a human perception of facial similarity. Images that include faces determined to be similar, based on the similarity information, may be provided to the user as search result images. The user then may provide feedback to indicate the user's perception of similarity between the query face and the search result images.

Hand-gesture input

The present disclosure provides an apparatus for efficiently providing character-based languages (e.g., Chinese, Japanese, and/or Korean) into portable electronic devices (e.g., smartphones, smartwatches, smartglasses, etc.). An example apparatus includes an input device configured to receiving a sequence of hand-qesture inputs and a a processor that performs operations for generating input for an electronic device corresponding to characters. The operations include detecting a pattern corresponding to each hand-gesture input in the sequence; determining a sequence of numeric values that correspond to the sequence of hand-gesture inputs based on the detected patterns; and as each input in the sequence of hand-gesture inputs is received, determining a list of one or more characters to display based, at least in part, on the sequence of numeric values and an index of characters.

Some automated and semi-automated tools for linear feature extraction in two and three dimensions

A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.

Home ui system for managing digital ink

A home user interface (UI) system for managing digital ink is provided. The home UI system includes a plurality of state sensors capable of detecting a state in a house or a change in the state, and a plurality of home-use devices that are provided in the house or that form part of the house and that each include a handwriting sensor capable of detecting handwriting made by a person. The home UI system further includes one or more notification units that are configured to notify the person of the existence of the home-use device or a detectable region of the handwriting sensor of the home-use device. The home UI system further includes a controller which, when it is determined that a notification is necessary from a detection result of one or more of the state sensors, instructs at least one of the notification units to carry out the notification.

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.

Image annotating method and electronic device

An image annotating method includes: acquiring an image collected at a terminal; acquiring voice information associated with the image; annotating the image according to the voice information; and storing an annotated result of the image.

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.

Systems and methods for managing meat cut quality

In some embodiments, apparatuses and methods are provided herein useful to ensuring quality of meat cuts. In some embodiments, a system for ensuring quality of meat cuts comprises a capture device comprising an image capture device configured to capture an image of a cut of meat, a depth sensor configured to capture depth data, a transceiver configured to transmit the image and the depth data, a microcontroller configured to control the image capture device, the depth sensor, and the transceiver, a database configured to store meat cut specifications, and the control circuit configured to receive, from the capture device, the image and the depth data, retrieve, from the database, a meat cut specification, evaluate the image of the cut of meat and the depth data associated with the cut of meat, and classify the cut of meat.

Information processing apparatus, information processing method, and program

There is provided an information processing apparatus including an image acquiring unit configured to acquire at least one captured image; and an associating unit configured to associate a first information corresponding to a first object and a second information corresponding to a second object, wherein the acquired at least one captured image comprises at least one selectable object depicted therewithin, and at least one of the first object and the second object corresponds to a respective one or ones of the at least one selectable object.

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.

Identity document validation method, system and computer program

A method of validating an identity document from a plurality of features extracted therefrom, wherein the features comprise a facial image and one or more personal detail elements of the identity document holder; and an identifier of an issuing authority who issued the identity document, wherein the method includes allowing an operator to define a value of a threshold for assessing the similarity of a pair of facial images, and wherein a measure of the similarity between the first facial image and the second facial image is calculated by applying a plurality of face recognition algorithms to the first facial image and the second facial image and calculating an accumulated score therefrom representing the degree of matching between the faces of the persons displayed in each facial image.

Computing system for extraction of textual elements from a document

Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text within a two-dimensional area represented by the document. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

Portable device with image sensor and illumination system for textile classification

The invention relates to a portable device (1100) comprising a bottom surface (BS) intended to be in contact with a textile (TXT). The portable device comprises an image sensor (5) for taking an image of a textile, and an illumination system (6) for illuminating a portion of the textile when said image is being taken. The portable device also comprises a control unit (8a) for executing an algorithm stored in the portable device, using the taken image as an input of said algorithm, to obtain a classification of the textile. The image sensor and the control unit are integrated within the portable device. The image sensor has an active surface sensitive to light, which is oriented compared to said bottom surface (BS), with an absolute value of the orientation angle being in the range 15-70 degrees; and/or the illumination system (6) has a light source oriented compared to the said bottom surface (BS), with an absolute value of the orientation angle being in the range 15-70 degrees.

Modifying binning operations

A data visualization technique is provided with the capability of manipulating bins of data through an interactive graphical presentation of displayed data. When a histogram is generated from stored data, a user may interact directly with the histogram columns to change columns position, width and height. A user, for example, may click and drag a particular side of a bin to change the lower or upper limit of the bin, click and drag the top of a bin to change the size/height of the bin (i.e., number of data points/elements within the bin), or click and drag the center of the bin to move or reposition the bin. The techniques may be applied to other graphical representations of data as well, such as splat graphical displays of data.

Filter for harmful training samples in online learning systems

A computing method receives a labeled sample from an annotator. The method may determine a plurality of reference model risk scores for the first labeled sample, where each reference model risk score corresponds to an amount of risk associated with adding the first labeled sample to a respective reference model of a plurality of reference models. The method may determine an overall risk score for the first labeled sample based on the plurality of reference model risk scores. The method may further determine a probe for confirmation of the first labeled sample and a trust score for the annotator by sending the probe to one or more annotators. In response to determining a trust score for the annotator the method may add the labeled sample to a ground truth or reject the labeled sample.

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.

Electronic Color Processing Devices, Systems and Methods

An electronic color recognition and enhancement device, system, and method aiding a user in recognition of color based patterns. The electronic color recognition and enhancement device, system, and method generally include a user device, including a processor, a visual input component, and a visual output component adapted to capture or record visual information and modify the contrast and/or color of a portion of the visual information to allow the user to recognize certain colors and/or patterns that otherwise may be difficult to recognize.

Deep learning-based image recognition method and apparatus

A deep learning-based image recognition method and apparatus are disclosed. The deep learning-based image recognition method comprises: training deep learning models based on deep learning frameworks, by using training image data, to obtain at least two deep learning models; selecting a predetermined number of deep learning models from the obtained deep learning models in a descending order of their recognition accuracies for verification image data, wherein the predetermined number is less than or equal to the number of the obtained deep learning models; and recognizing image data to be recognized using at least one of the selected deep learning models.

Methods and apparatus to identify media

Methods, apparatus, systems and articles of manufacture are disclosed to identify media. An example method includes: in response to a query, generating an adjusted sample media fingerprint by applying an adjustment to a sample media fingerprint; comparing the adjusted sample media fingerprint to a reference media fingerprint; and in response to the adjusted sample media fingerprint matching the reference media fingerprint, transmitting information associated with the reference media fingerprint and the adjustment.

System and Method of Advising Human Verification of Often-Confused Class Predictions

A method, system and a computer program product are provided for classifying elements in a ground truth training set by iteratively assigning machine-annotated training set elements to clusters which are analyzed to identify a prioritized cluster containing one or more elements which are frequently misclassified and display machine-annotated training set elements associated with the first prioritized cluster along with a warning that the first prioritized cluster contains one or more elements which are frequently misclassified to solicit verification or correction feedback from a human subject matter expert (SME) for inclusion in an accepted training set.

Method and system for creating aesthetic design at scale

The use of gestures are increasing frequently. Normally these gestures are disconnected with each other. Therefore, various methods have been used for creating the gestural language. The existing methods for creating gestural language is difficult to learn and lacks design aesthetics. A method and system for creating aesthetic design language using a plurality of gestures is provided. The system takes in to account of aesthetics of the generated form of gestures and the user's constraints of movement—degrees of freedom. The system is using a socio-techno system which aids the machine assisted creation of aesthetic language for gestural interactions. A grammar has also been defined for creating the gestural language based on the domain. In the final stage of the system, the grammar and the form symbols are chosen/selected/published to present the interaction language to the user.

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.

Computer vision as a service

A computer vision service includes technologies to, among other things, analyze computer vision or learning tasks requested by computer applications, select computer vision or learning algorithms to execute the requested tasks based on one or more performance capabilities of the computer vision or learning algorithms, perform the computer vision or learning tasks for the computer applications using the selected algorithms, and expose the results of performing the computer vision or learning tasks for use by the computer applications.

User interface to simulate target detection and recognition

A method is disclosed of providing a graphical user interface (GUI) for simulating target detection and recognition. The method includes providing a user entry area for receiving user entered ground truth attributes defining one or more respective simulated physical objects, and providing a user entry area for receiving user entered collection attributes defining one or more collections, each collection being a simulation of automated target recognition applied to simulated sensor output associated with simulated sensing of the one or more simulated physical objects. The method further includes simulating detection of the one or more simulated physical objects and recognition based on the ground truth attributes and the collection attributes, generating detection data about at least one detected object based on the simulated target detection, and displaying the detection data.

Information processing method and terminal device

Disclosed are an information processing method and a terminal device. The method comprises: acquiring first information, wherein the first information is information to be processed by a terminal device; calling an operation instruction in a calculation apparatus to calculate the first information so as to obtain second information; and outputting the second information. By means of the examples in the present disclosure, a calculation apparatus of a terminal device can be used to call an operation instruction to process first information, so as to output second information of a target desired by a user, thereby improving the information processing efficiency. The present technical solution has advantages of a fast computation speed and high efficiency.

Method and system for obtaining picture annotation data

The present disclosure provides a method and system for obtaining picture annotation data. The method comprises: obtaining a recognition result of a to-be-annotated picture; displaying the to-be-annotated picture and a corresponding recognition result on an annotation interface; using an annotator's selection of the recognition result in the annotation interface, to obtain annotation data of the to-be-annotated picture. According to the method and system for obtaining picture annotation data of the present disclosure, the annotator only needs to perform an operation of clicking the corresponding recognition result without manually inputting the name, and improves the annotation efficiency. The technical solution is particularly adapted for beforehand data preparation work of an image vertical type recognition algorithm, may substantially reduce costs of manually annotating pictures, and shorten the development cycle of picture recognition-type projects.

Ultrasound diagnostic imaging training apparatus, ultrasound diagnostic imaging apparatus, identification model training method, non-transitory recording medium storing computer readable training program, and ultrasound diagnostic apparatus

An ultrasound diagnostic imaging training apparatus for training an identification model to be used for identifying a target in an ultrasound image generated based on reflected ultrasound reflected from inside a subject includes a first hardware processor that extracts a first image from the ultrasound image used for training and generates teacher data in which a feature value of a second image included in the first image is associated with information relating to a likelihood of the target, the generation of the teacher data being based on the first image and preset reference data; and a second hardware processor that trains the identification model through machine learning using the teacher data.

Adjusting training set combination based on classification accuracy

Various embodiments are generally directed to techniques of adjusting the combination of the samples in a training batch or training set. Embodiments include techniques to determine an accuracy for each class of a classification model, for example. Based on the determined accuracies, the combination of the samples in the training batch may be adjusted or modified to improve the training of the classification model.

System and method for graph pattern analysis

In some example embodiments, a system and method are provided for graph pattern analysis. In example embodiments, pattern data of a primary network that includes data relating to relationships between entities are received. A reference matrix comprising a plurality of secondary network determined based on the pattern data of the primary network is generated A graphical display of the primary network and the reference matrix are displayed on a user interface. A selection of a secondary network from the plurality of secondary networks of the reference matrix is received. The selected secondary network has similar matching characteristics with at least a portion of the primary network. In response to the selection, the primary network is classified as a classification type related to the selected secondary network.

Camera-enabled machine learning for device control in a kitchen environment

A cooking control system accesses a set of training data used to train a machine learned model configured to detect smoke in a kitchen environment based on image data of a stovetop. The cooking control system receives real-time image data of a stovetop from a camera in the kitchen environment and applies the machine learned model to the image data to determine a likelihood that the image data includes smoke. If the cooking control system determines that the received images contain smoke, the cooking control system may perform one or more actions, such as disabling operation of the stovetop and sending an alert indicative of smoke to a user of he cooking control system or a local emergency department.

System and method for providing smart print settings

A system provides features for retrieving a print job. The print job includes print data, a source application and source job data type. The system determines if the print job requires a user activity analysis based on the source application and the source job data type. If user activity analysis is required, request a user-activity machine-learning model to provide user activity analysis data. The system establishes a relation between the print job and the user activity analysis data to generate input information to a job-data classification machine-learning model. The job-data classification machine-learning model provides print job data classification details as input information to a print setting recommendation learning model. The print setting recommendation machine-learning model processes the received print job data classification details and outputs a print setting recommendation. The system applies the print setting recommendation to the print job and processes the print job on the image processing device.

Information processing apparatus, information processing system, image capturing apparatus, information processing method, and memory

An information processing apparatus is provided which divides data for learning into first training data and second training data, stores the first training data and the second training data into a memory, and updates only the second training data without updating the first training data in a case where new characteristic data is obtained.

Methods and apparatus to identify media

Methods, apparatus, systems and articles of manufacture are disclosed to identify media. An example method includes: in response to a query, generating an adjusted sample media fingerprint by applying an adjustment to a sample media fingerprint; comparing the adjusted sample media fingerprint to a reference media fingerprint; and in response to the adjusted sample media fingerprint matching the reference media fingerprint, transmitting information associated with the reference media fingerprint and the adjustment.

Method and apparatus for video processing

Embodiments of the disclosure provides methods and apparatuses for video processing. In one embodiment, the video processing method comprises: obtaining at least one video from a video repository as a video to be processed; performing semantic recognition on the video in one or more semantic recognition dimensions to obtain one or more video label data items corresponding to the video in the one or more semantic recognition dimensions; generating at least one candidate label combination based on at least one of the one or more video label data items; determining, based on a target label combination selected by a user from the at least one candidate label combination, one or more video clips in the video corresponding to at least one video label in the target label combination; and generating at least one target video clip corresponding to the target label combination based on at least one of the one or more video clips.

Drive assist device

A drive assist devices include a display that displays an image around a vehicle imaged by an imaging device installed on the vehicle, a setting unit that sets a target designated by a user on the image as a recognition target, a detection unit that detects a state change of the recognition target on the image in a case where the recognition target is set, and a notification control unit that controls a notification device to notify the user of the detection result in a case where the state change of the set recognition target is detected.

Systems and methods for encoding image features of high-resolution digital images of biological specimens

An image analysis system for analyzing biological specimen images is disclosed. The system may include: a superpixel generator configured to obtain a biological specimen image and group pixels of the biological specimen image into a plurality of superpixels; a feature extractor configured to extract, from each superpixel in the plurality of superpixels, a feature vector comprising a plurality of image features; a clustering engine configured to assign the plurality of superpixels to a predefined number of clusters, each cluster being characterized by a centroid vector of feature vectors of superpixels assigned to the cluster; and a storage interface configured to store, for each superpixel in the plurality of superpixels, clustering information identifying the one cluster to which the superpixel is assigned. The system may also include a graph engine configured construct a graph based on the stored information, and use the graph to perform a graph-based image processing task.

Framework for building and sharing machine learning components

One embodiment of the present invention sets forth a technique for managing machine learning. The technique includes organizing a set of reusable components for performing machine learning under a framework. The technique also includes representing, within the framework, a machine learning model as a graph-based structure that includes nodes representing a subset of the reusable components and edges representing input-output relationships between pairs of the nodes. The technique further includes validating the machine learning model based on inputs and outputs associated with the nodes and the input-output relationships represented by the edges in the graph-based structure. Finally, the technique includes generating the machine learning model according to the graph-based structure and configurations for the subset of the reusable components.

Image Processing Methods

An image recognition approach employs both computer generated and manual image reviews to generate image tags characterizing an image. The computer generated and manual image reviews can be performed sequentially or in parallel. The generated image tags may be provided to a requester in real-time, be used to select an advertisement, and/or be used as the basis of an internet search. In some embodiments generated image tags are used as a basis for an upgraded image review. A confidence of a computer generated image review may be used to determine whether or not to perform a manual image review.

Food Inventory System and Method

A food inventory system, including a portable device which may include a bar code scanner and camera to add and remove inventory items to and from the inventory. The scanner may be mounted on an inventory storage container to facilitate inventory control from one or more domestic storage devices, including refrigerators, freezers, and pantries. The inventory system may display a table listing the inventory items along with variable details. Based on the food inventory list, the inventory system may suggest recipes, display the ingredients in stock for suggested recipes, and create a shopping list of the ingredients not in stock for a desired recipe. The portable device may be configured with wireless capability, connection to the internet, phones, tablets, laptops, and personal computer.

Training data collection for computer vision

Provided is a process that includes: determining that a training set lacks an image of an object with a given pose, context, or camera; composing, based on the determination, a video capture task; obtaining a candidate video; selecting a subset of frames of the candidate video as representative; determining that a given frame among the subset depicts the object from the given pose, context, or camera; and augmenting the training set with the given frame.

System, method, and computer-accessible medium for evaluating multi-dimensional synthetic data using integrated variants analysis

An exemplary system, method, and computer-accessible medium can include, for example, receiving an original dataset(s), receiving a synthetic dataset(s), training a model(s) using the original dataset(s) and the synthetic dataset(s), and evaluating the synthetic dataset(s) based on the training of the model(s). The model(s) can include a first model and a second model, and the first model can be trained using the original dataset(s) and the second model can be trained using the synthetic dataset(s). The synthetic dataset(s) can be evaluated by comparing first results from the training of the first model to second results from the training of the second model.

Interactive visualization of machine-learning performance

Methods, computer systems, computer-storage media, and graphical user interfaces are provided for visualizing a performance of a machine-learned model. An interactive graphical user interface includes an item representation display area that displays a plurality of item representations corresponding to a plurality of items processed by the machine-learned model. The plurality of item representations are arranged according to scores assigned to the plurality of items by the machine-learned model. Further, each of the plurality of item representations is visually configured to represent a label assigned to a corresponding item.

Methods and systems for content processing

Mobile phones and other portable devices are equipped with a variety of technologies by which existing functionality can be improved, and new functionality can be provided. Some aspects relate to visual search capabilities, and determining appropriate actions responsive to different image inputs. Others relate to processing of image data. Still others concern metadata generation, processing, and representation. Yet others concern user interface improvements. Other aspects relate to imaging architectures, in which a mobile phone's image sensor is one in a chain of stages that successively act on packetized instructions/data, to capture and later process imagery. Still other aspects relate to distribution of processing tasks between the mobile device and remote resources (“the cloud”). Elemental image processing (e.g., simple filtering and edge detection) can be performed on the mobile phone, while other operations can be referred out to remote service providers. The remote service providers can be selected using techniques such as reverse auctions, through which they compete for processing tasks. A great number of other features and arrangements are also detailed.

Systems and methods for generating machine learning applications

Systems and methods for generating prebuilt machine learning framework objects comprising sets of prebuilt machine learning components and one or more data mapping requirements. The components are associated with a respective machine learning service. One or more datasets are obtained. A user-specified context for creating a particular machine learning application is obtained. A particular prebuilt object is selected based on the datasets and the context. One more candidate data mappings are identified based on the data mapping requirements and the datasets. A particular data mapping is selected. A particular set of prebuilt components is selected from the plurality of prebuilt components. The particular machine learning application is generated from the particular prebuilt object based on the particular data mapping and the particular set of prebuilt components, the particular machine learning application comprising an executable application. The machine learning application is deployed.

Imaging control apparatus, storage system, and storage medium

There is provided an imaging control apparatus including an imaging control section configured to control an imaging section to capture a predetermined area in a body cavity, a comparison section configured to compare a captured image captured by the imaging section with a reference image, and a storage control section configured to execute a control to store the captured image in response to a comparison result by the comparison section.

Image analyzing device and image analyzing method

An image analyzing device comprises: a detection unit configured to execute detection processing for detecting a predetermined object included in an image, using a plurality of different object models that are for detecting the predetermined object; a display control unit configured to control a display to display information indicating each of the plurality of different object models and information indicating each of results of the detection processing related to each of the plurality of different object models; a reception unit configured to receive selection of at least one object model from among the plurality of different object models which are pieces of information displayed by the display control unit; and a setting unit configured to set an object model to be used in the detection processing, based on the selection received by the reception unit.

Systems and Methods for Automated Code Validation

Systems and methods in accordance with embodiments of the invention can automatically track the creation of documents, such as source code files and unit tests, along with the development of those documents. The document creation and development workflow can be automatically validated against a defined set of standards to ensure that the documents are properly created. The review of the documents can also be automatically validated to ensure that the review process is properly completed. A variety of metrics can be generated regarding errors and issues identified during the validation processes. These metrics can be used to identify common issues, automatically generate proactive suggestions to avoid issues during document creation and testing, and/or generate developer profiles indicating the performance of particular developers.

Seismic data representation and comparison

A seismic dataset and a task to be performed with the seismic dataset may be received. A representative seismic line representative of the seismic dataset may be generated. The representative seismic line may include pixel data representative of the seismic dataset. Based on the representative seismic line, the task may be performed. The task may include at least finding an analogous geological region by searching for an analogous seismic dataset existing in a seismic database by comparing the representative seismic line with the analogous seismic dataset's representative seismic line.

Performance Grinding Solutions

The present application relates to systems and methods for obtaining real-time abrasion data. An example computer-implemented method could include receiving, at a computing device, sensor data from one or more sensors. The one or more sensors are disposed in proximity to an abrasive product or a workpiece associated with the abrasive product. The one or more sensors are configured to collect abrasion operational data associated with an abrasive operation involving the abrasive product or the workpiece. The computer-implemented method could further include training, based on the sensor data, a machine learning system to determine product specific information of the abrasive product and/or workpiece specific information. The computer-implemented method could also include providing the trained machine learning system using the computing device.

Information processing system, information processing method, information processing apparatus, control method therefor, and storage medium storing control program therefor

This invention relates to an information processing apparatus which assists diagnosis based on a tissue sample image obtained by staining and capturing a tissue. The information processing apparatus receives and analyzes lower magnification image data among a plurality of image data obtained at different magnifications for an area image selected in the tissue sample image. Based on the analysis result, the information processing apparatus determines whether analysis based on higher magnification image data is necessary. When analysis based on the higher magnification image data is necessary, the information processing apparatus notifies a request of transmitting the higher magnification image data for the area image, receives and analyzes the higher magnification image data transmitted in response to the transmission request, and transmits the analysis result. This arrangement can quickly provide high-accuracy diagnosis assistance for a tissue sample image from a pathologist regardless of the restriction of the transmission capacity.

Interactive analysis of data based on progressive visualizations

Interactive analysis of data based on progressive visualizations is disclosed. One example is a system including a data module, a visualization module, an interaction module, and an analytics module. The data module processes a plurality of data elements. The visualization module progressively displays, via an interactive graphical user interface, an overview visualization of a sub-plurality of the plurality of data elements, the overview visualization based on at least one of data resolution and display resolution, and a detailed visualization based on an interaction with the overview visualization. The interaction module processes the interaction with the overview visualization. The analytics module analyzes the interaction to generate a deployment rule.

Visual feature tagging in multi-view interactive digital media representations

Provided are mechanisms and processes for visual feature tagging in multi-view interactive digital media representations (MIDMRs). In one example, a process includes receiving a visual feature tagging request that includes an MIDMR of an object to be searched, where the MIDMR includes spatial information, scale information, and different viewpoint images of the object. A visual feature in the MIDMR is identified, and visual feature correspondence information is created that links information identifying the visual feature with locations in the viewpoint images. At least one image associated with the MIDMR is transmitted in response to the feature tagging request.

Systems and user interfaces for dynamic and interactive investigation of bad actor behavior based on automatic clustering of related data in various data structures

Embodiments of the present disclosure relate to a data analysis system that may automatically generate memory-efficient clustered data structures, automatically analyze those clustered data structures, automatically tag and group those clustered data structures, and provide results of the automated analysis and grouping in an optimized way to an analyst. The automated analysis of the clustered data structures (also referred to herein as data clusters) may include an automated application of various criteria or rules so as to generate a tiled display of the groups of related data clusters such that the analyst may quickly and efficiently evaluate the groups of data clusters. In particular, the groups of data clusters may be dynamically re-grouped and/or filtered in an interactive user interface so as to enable an analyst to quickly navigate among information associated with various groups of data clusters and efficiently evaluate those data clusters in the context of, for example, a fraud investigation.

Apparatus for automated cellular bioinformatics

An automated system that conducts, monitors, and validates a cell-line-based biological experiment including one or more treatment compounds or other external stimuli. In one preferred embodiment, the system comprises two principal subsystems, and optionally accessory subsystems. A first principal subsystem is an automated laboratory experiment manager for designing the biological experiment, for constructing an assay plate used to conduct the biological experiment, and for managing one or more of the processes that constitute the biological experiment. A second principal subsystem is an automated data analysis manager for analyzing images, for instance produced by the image production system, to detect image data including biological markers and objects, for analyzing the resulting image data to produce biological data, and for analyzing the biological data to produce biological phenotypes and treatment compound signatures.

Apparatus and method for the detection and classification of articles using flow cytometry techniques

This invention concerns a flow apparatus and method for the detection of particles in a sample. Particles are moved, substantially one at a time, in a fluid flow stream. An incident beam of illumination is provided so as to be directed at the particles in the flow stream. Data associated with each moving particle as it passes through the beam of illumination is detected. A class of particles is established, these particles having common characteristics based on the data detected from such class of particles. The data is then stored. Such stored data is compared to data detected from sample particles of an unknown class. A determination is then made that particles from the unknown class belong to the established class as a result of matching respective data.

一种管理图像框的方法、系统、设备及介质

本发明提供一种管理图像框的方法、系统、设备及介质，通过对图片中的目标对象进行预标注，获取预标注后的图像框；根据预标注后的图像框确定图像框从属关系，并按照图像框从属关系识别预标注后的图像框是否存在错误标注；并修改存在错误标注的图像框。其中，错误标注包括以下至少之一：将从属于某一图像框的另一图像框标注为不属于某一图像框、将不从属于某一图像框的另一图像框标注为从属于某一图像框。本发明先通过预设算法对图像中的目标对象进行预标注，得到多个图像框；再在预标注的基础上对存在错误标注的图像框进行纠正，使得对图像中的目标对象进行的标注完全正确。本发明可以提高图像检测算法在安防、智能交通等领域的准确率。

Methods and systems for content processing

Cell phones and other portable devices are equipped with a variety of technologies by which existing functionality can be improved, and new functionality can be provided. Some aspects relate to data driven imaging architectures, in which a cell phone's image sensor is one in a chain of stages that successively act on packetized instructions/data, to capture and later process imagery. Other aspects relate to distribution of processing tasks between the device and remote resources (“the cloud”). Elemental image processing, such as filtering and edge detection—and even some simpler template matching operations—may be performed on the cell phone. Other operations are referred out to remote service providers. The remote service providers can be identified using techniques such as a reverse auction, though which they compete for processing tasks. Other aspects of the disclosed technologies relate to visual search capabilities, and determining appropriate actions responsive to different image inputs. Still others concern metadata generation, processing, and representation. Yet others relate to coping with fixed focus limitations of cell phone cameras, e.g., in reading digital watermark data. Still others concern user interface improvements. A great number of other features and arrangements are also detailed.

Image Processing Apparatus, Image Processing Method and Visual Inspection System

검사의 대상이 되는 제품(502)을 전자카메라(102)에 의해 촬상하여 화상이 컨트롤러(100)에 출력된다. 오퍼레이터는 콘솔(101)을 조작하고, 컨트롤러에 대하여 소망하는 검사 종별을 지정하는 정보를 준다. 컨트롤러는 소망하는 검사 종별의 정보가 주어지면 거기에 따라 당해 소망하는 검사 종별의 검사에 알맞는 대조 프로그램의 설정에 필요한 조작을 비디오 모니터(103)를 통해서 오퍼레이터에 대해 안내한다. 오퍼레이터는 표시되는 안내에 따라 콘솔을 통해 조작함으로써 컨트롤러에 있어서 대조 프로그램을 설정할 수 있다. 대조 프로그램이 설정되면 컨트롤러에서는 주어진 제품화상과 미리 준비된 기준화상이 설정된 대조 프로그램에 따라서 대조되고 제품이 시각적으로 검사된다. The product 502 to be inspected is picked up by the electronic camera 102 and an image is output to the controller 100. The operator operates the console 101 and gives information specifying the desired inspection type for the controller. When the controller is given the information of the desired inspection type, the controller guides the operator via the video monitor 103 to the operation necessary for setting the control program suitable for the inspection of the desired inspection type. The operator can set the matching program in the controller by operating through the console according to the guidance displayed. When a control program is set up, the controller compares the given product picture and the prepared reference picture according to the setup control program and visually inspects the product.

Automatic labeling method and device for industrial product image, electronic equipment and storage medium

本发明提供了一种工业品图像的自动标注方法、装置、电子设备和存储介质，通过获取物体的待标注图像和分类信息；对所述待标注图像进行分割处理，以分割出所述待标注物体各组成部件的独立图像；根据所述分类信息，分别对所述待标注物体各组成部件的独立图像进行识别，以得到各组成部件的类型识别结果；根据所述类型识别结果，在所述待标注图像中的各组成部件处添加对应的标签，得到初步标注图像；显示所述初步标注图像以获取修改信息，从而生成最终的标注图像；从而可对由多个部件装配而成的物体中的各部件进行自动标注，有利于提高标注效率，降低成本。

Data labeling method, device, system and terminal equipment

本说明书实施例提出了一种数据标注方法、装置、系统和终端设备，其中，上述数据标注方法中，第一终端设备接收标注平台服务器发送的待标注任务包，然后从待标注任务包中获取当前待标注的图片，并获取当前待标注的图片的访问链接，第一终端设备展示上述访问链接，以供第二终端设备根据上述访问链接，获得当前待标注的图片，进行描绘操作，从而可以实现将在第一终端设备上无法完成标注的图片发送到第二终端设备，对图片中标注对象的轮廓进行精准描绘。然后，第一终端设备获取第二终端设备的描绘信息，对上述描绘信息进行编号并输入与上述描绘信息对应的文本信息，从而完成当前待标注的图片的标注操作。

Methods and systems for content processing

모바일 폰들 및 다른 휴대용 디바이스들은 다양한 기술들이 장착되고, 그에 의해 기존의 기능이 개선될 수 있고, 새로운 기능이 제공될 수 있다. 일부 양태들은 비주얼 검색 능력과, 상이한 이미지 입력들에 응답하는 적합한 동작들을 결정하는 것에 관련된다. 다른 양태들은 이미지 데이터의 처리에 관련된다. 또 다른 양태들은 메타데이터 생성, 처리 및 제공에 관련된다. 또 다른 양태들은 이용자 인터페이스 개선들에 관련된다. 다른 양태들은 이미징 아키텍처들에 관련되며, 이 중 모바일 폰의 이미지 센서는 이미지를 캡처하여 나중에 처리하기 위해 패킷화된 명령어들/데이터에 대해 연속적으로 동작하는 스테이지들의 체인 중 하나이다. 또 다른 양태들은 모바일 디바이스와 원격 리소스들("클라우드") 사이의 처리 작업들의 분배에 관련된다. 요소적 이미지 처리(예를 들면, 간단한 필터링 및 에지 검출)가 모바일 폰 상에서 실행될 수 있지만, 다른 동작들은 원격 서비스 제공자들에 참조될 수 있다. 원격 서비스 제공자들은 역경매들과 같은 기술들을 이용하여 선택될 수 있고, 이를 통해 이들은 작업들을 처리하기 위해 경합한다. 다수의 다른 특징들 및 어레인지먼트들이 또한 상술된다.

Database display and search method

A method for efficiently and expediently searching a database so that large quantities of data may be visualized to reveal and readily identify underlying patterns and/or obscure, latent relationships among the individual data elements, comprising: selecting a particular aspect of relationship information; scanning the data items and their associated information to determine the existence of the selected aspect of relationship information; selecting an object data item from the data items; grouping a plurality of data items related to the object data item into a specific group having a defined relationship with at least one other related data item contained within the specific group; identifying each data item contained within the same group as the object data item; tallying the magnitude associated with the selected aspect of relationship information for each data item with respect to every other data item in the database; and mapping the object data item and the other data items identified as being contained within the same group as the object data item onto a Cartesian coordinate, thus generating an image for display.

Training annotation of objects in an image

Изобретение относится к области вычислительной техники для обработки изображений. Технический результат заключается в улучшении аннотирования объектов в изображении за счет алгоритма машинного обучения. Компьютеризованный способ обучения, включающий следующие операции: получают доступ к данным изображения; используют алгоритм машинного обучения, чтобы получить машинные аннотации объектов в одном или более масштабах указанного изображения; формируют на дисплее просмотровое окно, конфигурируемое на основе коэффициента увеличения; имитируют ручное аннотирование объекта в различных масштабах и/или в различных частях каждого масштаба изображения; используют имитированные ручные аннотации в качестве различных обучающих входов в алгоритм машинного обучения; квантифицируют изменения в различных результирующих машинных аннотациях объектов; выбирают коэффициент увеличения и параметр пространственного смещения на основе идентифицированной имитированной ручной аннотации и после приема входных данных используют ручное аннотирование объекта пользователем в качестве обучающего входа в алгоритм машинного обучения. 6 н. и 14 з.п ф-лы, 7 ил. РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 739 713 C1 (51) МПК G06K 9/52 (2006.01) G06K 9/62 (2006.01) G06T 7/11 (2017.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06K 9/52 (2020.08); G06K 9/62 (2020.08); G06T 7/11 (2020.08) (21)(22) Заявка: 2019120949, 05.12.2017 (24) Дата начала отсчета срока действия патента: Дата регистрации: 28.12.2020 (73) Патентообладатель(и): КОНИНКЛЕЙКЕ ФИЛИПС Н.В. (NL) (56) Список документов, цитированных в отчете о поиске: US 2014/0219548 A1, 07.08.2014. US 2014/0233826 A1, 21.08.2014. US 2016/0171682 A1, 16.06.2016. EP 2854100 A1, 01.04.2015. RU 2439686 C2, 10.01.2012. 08.12.2016 EP 16202827.8 (45) Опубликовано: 28.12.2020 Бюл. № 1 (85) Дата начала рассмотрения заявки PCT на национальной фазе: 08.07.2019 (86) Заявка PCT: 2 7 3 9 7 1 3 (87) Публикация заявки PCT: ...

Information identification method and device, electronic equipment and computer readable storage medium

本公开是关于一种信息识别方法及装置、电子设备和计算机可读存储介质，其中，信息识别方法包括：根据待识别窗口属性信息查找待识别窗口；响应于查找到待识别窗口，获取待识别窗口绘制工具；根据预先确定的待识别区域位置信息，使用待识别窗口绘制工具对待识别区域进行截图，其中，待识别区域位于待识别窗口中；识别截图内容。本公开实施例，通过响应于查找到待识别窗口，才获取待识别窗口绘制工具，以确保待识别窗口出现时才进行截图识别，从而保证识别准确性，同时，使用待识别窗口绘制工具而非桌面DC对待识别区域进行截图，以确保待识别区域被其他窗口内容遮挡时，仍能被正确识别。

Home automation system using real-time indoor image

본 발명은 실시간 실내 영상을 이용하여 실내에 비치된 기기를 제어하는 홈 오토메이션 시스템에 관한 발명이다. 본 발명에서는 실시간 실내 영상을 디스플레이 하는 터치스크린에 사용자로부터 터치 입력을 받아 실내에 비치된 기기들을 제어한다. 본 발명에 따르면 사용자는 제어된 기기들을 시각적으로 즉각 확인하는 것이 가능하다. 또한 본 발명에 따르면 사용자는 기기마다 서로 다른 상세화면에 진입할 필요 없이 실시간 실내 영상이 디스플레이 되는 화면 상에서 기기를 제어하는 것이 가능하다. The present invention relates to a home automation system for controlling devices installed indoors using real-time indoor images. In the present invention, devices installed indoors are controlled by receiving a touch input from a user on a touch screen that displays real-time indoor images. According to the present invention, it is possible for the user to visually check the controlled devices immediately. In addition, according to the present invention, it is possible for a user to control a device on a screen on which a real-time indoor image is displayed without having to enter a different detailed screen for each device.

System and method for integrating machine learning and mass outsourcing data tagging

一种用于机器学习系统的数据标注系统包括计算系统，该计算系统被配置成执行用于生成输入数据的数据标注的机器学习算法。该计算系统进一步被配置成：执行用于将机器学习算法的结果和预测传达给非专家工作者以供审查的接口。该接口使用可视化和自然语言与非专家工作者进行通信以引出反馈，从而改进机器学习算法的性能。

Video pushing method, device, computer equipment and storage medium

本申请是关于一种视频推送方法，该方法包括：获取第一视频中的N个候选封面；通过视频封面确定模型获得N个候选封面各自的预测置信度；该视频封面确定模型是根据第二视频中的K个候选封面，以及K个候选封面各自的用户操作数据进行强化学习获得的卷积神经网络模型；根据N个候选封面各自的预测置信度，从N个候选封面中获取第一视频的视频封面；根据第一视频的视频封面向终端推送第一视频。由于视频封面确定模型是根据用户对不同封面的相同视频执行的操作进行强化训练的卷积神经网络模型，综合考虑了用户对视频封面的选择操作，提高了后续通过训练出的模型确定视频封面的准确性。

Information processing apparatus, control method thereof, and memory

本发明提供一种信息处理设备及其控制方法和存储器。该信息处理设备将用于学习的数据划分成第一训练数据和第二训练数据，将第一训练数据和第二训练数据存储到存储器中，并且在获得新的特征数据的情况下仅更新第二训练数据而不更新第一训练数据。

Dynamic self-learning medical image method and system

A method and system for creating a dynamic self-learning medical image network system, wherein the method includes receiving, from a first node initial user interaction data pertaining to one or more user interactions with the one or more initially obtained medical images; training a deep learning algorithm based at least in part on the initial user interaction data received from the node; and transmitting an instance of the trained deep learning algorithm to the first node and/or to one or more additional nodes, wherein at each respective node to which the instance of the trained deep learning algorithm is transmitted, the trained deep learning algorithm is applied to respective one or more subsequently obtained medical images in order to obtain a result.

System, method and computer program product for classifying a plurality of items

시스템, 방법 및 컴퓨터 소프트웨어 제품이 개시되며, 시스템은 결함들을 분류할 수 있고, 그리고 시스템은: 하드웨어-기반 GUI 컴포넌트; 및 프로세싱 및 메모리 회로를 포함하며, 프로세싱 및 메모리 회로는: a. 복수의 결함들 및 복수의 결함들의 속성 값들의 정보를 제공하는(informative) 데이터를 획득 시에, 복수의 클래스들로의 복수의 결함들의 초기 분류를 생성하기 위해 속성 값들을 사용하고; b. 주어진 클래스(given class)에 대해, 하드웨어-기반 GUI 컴포넌트에 의해, 낮은 가능성(likelihood)으로 주어진 클래스로 초기에 분류된 적어도 하나의 결함의 이미지를 사용자에게 제시하고 ― 이미지는 가장 높은 가능성으로 주어진 클래스로 초기에 분류된 하나 또는 그 초과의 결함들의 이미지들과 함께 제시됨 ―; 그리고 c. 하드웨어-기반 GUI 컴포넌트를 사용하여, 적어도 하나의 결함이, 주어진 클래스로 분류되는 것을 사용자가 확인(confirming)하는 것을 조건으로, 적어도 하나의 결함을 주어진 클래스에 속하는 것으로 표시하도록 구성된다.

Formula inputting method, apparatus and electronic device

사용자의 필기 입력을 수신하는 단계, 상기 사용자의 필기 입력을 기반으로 필기 컨텐트를 획득하고, 상기 필기 컨텐트를 기반으로 적어도 하나 이상의 추천 컨텐트를 결정하는 단계, 상기 사용자 인터페이스는 상기 필기 컨텐트 및 상기 하나 이상(one or more)의 추천 컨텐트를 표시하는 단계를 포함하는 공식 입력 방법을 제공한다. Receiving a user's handwriting input, obtaining handwritten content based on the user's handwriting input, and determining at least one recommended content based on the handwritten content, wherein the user interface includes the handwritten content and the one or more items Provides an official input method including the step of displaying (one or more) recommended content.

For detecting the system of the uneven factor in web shaped material

本公开涉及用于检测所述不均匀形态的存在并提供表征每个类型不均匀形态的严重性的输出的系统。所述系统包括一种计算机化评级工具，所述计算机化评级工具帮助用户有效和一致地为代表给定产品样品的大型训练图像集合分配专家评级（即标签）。此外，所述评级软件开发一种模型，所述模型允许计算机化检测系统在制成幅材中实时地检测不均匀形态的存在，并以连续的数值范围提供表征每个形态的严重级别的输出。所述系统还包括算法和硬件方法，用以显著提高所述检测系统的吞吐量。

Human ring labeling method and device based on active learning

本发明涉及了一种基于主动学习的人环标注方法及装置，其中该方法包括：利用已标注样本数据建立目标检测模型；将未标注样本数据输入目标检测模型进行测试以计算未标注样本数据的分类存疑度、定位稳定性和定位紧密度；根据分类存疑度、定位稳定性和定位紧密度计算未标注样本的综合得分；提取综合得分在预定范围内的未标注样本数据进行人工标注；利用经过人工标注的样本数据优化目标检测模型；循环执行前四个步骤直至目标检测模型符合终止条件，并基于该训练过的目标检测模型为剩余未标注样本数据进行标注。利用本发明的方法缓解目前计算机视觉领域对图像标注的高质量要求与标注过程耗时费力的供需矛盾，从而更有效地进行样本标注。

Defect classification apparatus, automatic defect classification method, defect inspection method, and processing apparatus

Correlated slice and view image annotation for machine learning

Methods and systems for allowing users operators to quickly and easily (i) review the products of machine learning algorithm(s) to evaluate their accuracy, (ii) make corrections to such products, and (iii) compile feedback for retraining the algorithm(s) are disclosed. An example method includes acquiring a plurality of correlated images of a sample, determining one or more features in each image of the plurality of correlated images, and then determining a relationship between at least a first feature in a first image of the plurality of correlated images and at least a second feature in a second image of the plurality of images. Then, when characteristic information is determined about the first feature, it is associated with both the first feature in the first image and the second feature in the second image based on the relationship

2d/3d integrated contour editor

用于完全集成轮廓编辑器的系统和方法。在本发明的示例性实施例中，随3D界面提供2D界面，该2D界面使得用户可以在某时限定和编辑在数据组的一个图像片段上的轮廓，该3D界面使得用户可以作用到整个3D数据组。2D界面和3D界面完全集成，在2D界面中限定或编辑的轮廓同时显示在3D数据组的相应位置中。2D轮廓能够利用多种容易获得的工具来创建和编辑，在用户指示选定的关注区域时，在3D数据组内指示的关注区域使得相关的2D片段被显示在2D界面中。在本发明的示例性实施例中，系统能够基于用户限定的顶部轮廓和底部轮廓而自动产生轮廓，并且能够利用多个数据组重新映射轮廓。

Active learning for defect classifier training

Methods and systems for performing active learning for defect classifiers are provided. One system includes one or more computer subsystems configured for performing active learning for training a defect classifier. The active learning includes applying an acquisition function to data points for the specimen. The acquisition function selects one or more of the data points based on uncertainty estimations associated with the data points. The active learning also includes acquiring labels for the selected one or more data points and generating a set of labeled data that includes the selected one or more data points and the acquired labels. The computer subsystem(s) are also configured for training the defect classifier using the set of labeled data. The defect classifier is configured for classifying defects detected on the specimen using the images generated by the imaging subsystem.

Artificial neural network class-based pruning

특정 감시 상황에 대한 인공 뉴럴 네트워크를 구성하기 위한 기법들을 구현하는 그리고 사용하는 방법 및 장치가 제공되고, 여기에는 컴퓨터 프로그램물들이 포함된다. 감시 상황에 대한 특징을 나타내는 일정 개수의 오브젝트 클래스들이 선택된다. 이러한 오브젝트 클래스들은 인공 뉴럴 네트워크가 훈련되는 전체 개수의 오브젝트 클래스들의 서브세트를 형성한다. 인공 뉴럴 네트워크 내의 뉴런들에 대한 활성화 빈도 값들을 포함하는 데이터베이스가 액세스된다. 활성화 빈도 값들은 오브젝트 클래스에 따라 달라지는 값들이다. 선택된 오브젝트 클래스들의 서브세트에 대해 임계 값보다 작은 활성화 빈도 값들을 갖는 그러한 뉴런들이 인공 뉴럴 네트워크로부터 제거된다. Methods and apparatus for implementing and using techniques for constructing an artificial neural network for a particular surveillance situation are provided, including computer programs. A certain number of object classes are selected that represent characteristics of the monitoring situation. These object classes form a subset of the total number of object classes in which the artificial neural network is trained. A database containing activation frequency values for neurons in an artificial neural network is accessed. The activation frequency values are values depending on the object class. Those neurons with activation frequency values less than the threshold for a subset of the selected object classes are removed from the artificial neural network.

Device and method for analyzing imported video

FIELD: computer equipment.SUBSTANCE: invention relates to the computer equipment. Device for analyzing imported video comprises: a memory, a database for storing metadata, a graphical user interface and a data processing device, wherein data processing device is configured to download video in public format into memory and import loaded video into software (SW) device for analyzing imported video, wherein the SW enables decompression and analysis of imported video to generate metadata characterizing data on all objects in video, and for recording said metadata in a database.EFFECT: high speed of searching for a required event or object in imported video received from a third-party device.33 cl, 2 dwg РОССИЙСКАЯ ФЕДЕРАЦИЯ (19) RU (11) (13) 2 688 757 C1 (51) МПК G06F 16/70 (2019.01) G06K 9/62 (2006.01) G06T 7/00 (2006.01) ФЕДЕРАЛЬНАЯ СЛУЖБА ПО ИНТЕЛЛЕКТУАЛЬНОЙ СОБСТВЕННОСТИ (12) ОПИСАНИЕ ИЗОБРЕТЕНИЯ К ПАТЕНТУ (52) СПК G06F 16/70 (2019.02); G06K 9/62 (2019.02); G06T 7/00 (2019.02); G06F 17/40 (2019.02); G06F 16/74 (2019.02); H04N 21/43 (2019.02); H04N 21/434 (2019.02) (21)(22) Заявка: 2018131164, 29.08.2018 29.08.2018 (73) Патентообладатель(и): ООО "Ай Ти Ви групп" (RU) Дата регистрации: 22.05.2019 (45) Опубликовано: 22.05.2019 Бюл. № 15 2 6 8 8 7 5 7 R U (54) УСТРОЙСТВО И СПОСОБ ДЛЯ АНАЛИЗА ИМПОРТИРОВАННОГО ВИДЕО (57) Реферат: Изобретение относится к вычислительной загрузки видео в общедоступном формате в технике. Технический результат − повышение память и импорта загруженного видео в скорости поиска необходимого события или программное обеспечение (ПО) устройства для объекта в импортированном видео, полученном анализа импортированного видео, причем ПО от стороннего устройства. Устройство для позволяет выполнять декомпрессию и анализ анализа импортированного видео содержит: импортированного видео для формирования память, базу данных для хранения метаданных, метаданных, характеризующих данные обо всех графический пользовательский интерфейс и объектах в видео, и для ...

System and method for graph pattern analysis

In some example embodiments, a system and method are provided for graph pattern analysis. In example embodiments, pattern data of a primary network that includes data relating to relationships between entities are received. A secondary network based on the pattern data of the primary network is generated by using an algorithm that processes pattern characteristics extracted from the pattern data. The generated secondary network is provided for further analysis.

SYSTEM AND METHOD FOR FINDING AND CLASSIFYING LINES IN A PICTURE THROUGH A LAYERING SYSTEM

Die vorliegende Erfindung stellt ein System samt zugehörigem Verfahren zum Auffinden von Linienmerkmalen in einem Bild bereit, das es erlaubt, mehrere Linien effizient und präzise zu identifizieren und zu charakterisieren. Wenn Linien identifiziert werden, kann der Benutzer das System so trainieren, dass vorgegebene Etiketten (z. B. Textetiketten) in Bezug auf solche Linien zugeordnet werden. Diese Etiketten können dazu verwendet werden, Neuronalnetz-Klassifizierer zu definieren. Das neuronale Netz wird während der Laufzeit betrieben, um Linien in einem Laufzeitbild, die mittels eines Linienauffindungsprozesses aufgefunden werden, zu identifizieren und zu bewerten. Die aufgefundenen Linien können dem Benutzer zusammen mit Etiketten und einer zugeordneten Wahrscheinlichkeitsbewertungskarte basierend auf den Neuronalnetzergebnissen angezeigt werden. Bei Linien ohne Kennzeichnung ist im Allgemeinen davon auszugehen, dass sie eine niedrige Bewertungsziffer haben, und diese werden durch das Interface entweder nicht mit einem Flag markiert oder als nicht relevant identifiziert. The present invention provides a system and associated method for finding line features in an image that allows efficient and precise identification and characterization of multiple lines. When lines are identified, the user can train the system to associate predetermined labels (eg, text labels) with respect to such lines. These labels can be used to define neural network classifiers. The neural network operates at runtime to identify and evaluate lines in a runtime image that are found by a line discovery process. The found lines may be displayed to the user along with labels and an associated probability score map based on the neural net results. Lines without labels are generally considered to have a low score, and are either flagged or not considered relevant by the interface.

Structural annotation

本发明涉及一种创建一个或多个经注释感知输入的计算机实施方法，该方法包括：在注释计算机系统中：接收多个捕获帧，每一帧均包括3D结构点集，其中捕获公共结构组件的至少一部分；计算多帧中至少一个参考帧内的参考位置；通过基于该帧内的参考位置选择性提取参考帧的3D结构点来生成公共结构组件的3D模型；基于3D模型与多帧的目标帧中公共结构组件自动对齐，确定该目标帧内3D模型的对齐模型位置；将对齐模型位置的注释数据与该目标帧的至少一个感知输入相关联地存储在计算机存储器中，以便注释其中的公共结构组件。

Inspection device

Pattern discovery, prediction and causal effect estimation in treatment discontinuation

With a trained, computerized discontinuation predictor machine learning component (MLC), predict, based on an input time series, a time when a subject will discontinue a course of medical treatment; with a trained, computerized pattern behavior extractor MLC, extract from said input time series the top k discriminatory sequences via discriminatory sub-sequence mining (said top k discriminatory sequences differentiate between first and second classes of interest to provide a hypothesis for downstream analysis of a cause of discontinuing said course of treatment). With a trained, causal effect estimator computerized MLC, determine a reason why said subject will discontinue said course of medical treatment, based on said top k discriminatory sequences and additional data; and with a computerized user interface, provide said time and said reason why to a responsible party to initiate an intervention.

Signal interpretation engine

A signal interpretation engine apparatus and method are disclosed as including a computer programmed to run a feature expansion module, a weight table module, a consolidation module, and a map generation module. The feature expansion module contains feature operators for operating on a signal to expand the signal to form a feature map of feature segments. Each feature segment corresponds to a unique representation of the signal created by a feature operator from the signal across an epoch. An epoch corresponds to an event within a time segment. A consolidation module applies aggregators to consolidate the inner products or superposition segments into a distribution function representing an attribute over a domain reflecting a selected weight table, aggregator, and event type, corresponding to each value of the attribute.

Method and apparatus for automated cellular bioinformatics

Processing sensor logs

A method of processing sensor logs is described. The method includes accessing a first sensor log and a corresponding first reference log. Each of the first sensor log and the first reference log includes a series of measured values of a parameter according to a first time series. The method also includes accessing a second sensor log and a corresponding second reference log. Each of the second sensor log and the second reference log includes a series of measured values of a parameter according to a second time series. The method also includes dynamically time warping the first reference log and/or and second reference log by a first transformation between the first time series and a common time-frame and/or a second transformation between the second time series and the common time-frame. The method also includes generating first and second warped sensor logs by applying the or each transformation to the corresponding ones of the first and second sensor logs.

Relevance feedback system of multimedia data

본 발명은 사용자의 피드백(relevance feedback)을 사용해서 이미지 특징소(image feature)의 가중치(weight)를 결정하는 시스템에서, 최근 사용자 피드백 정보와 전체 피드백 정보를 함께 고려하여 이미지 특징소의 가중치를 결정하는 방법과 그 데이타 특징소 정보의 생성방법에 관한 것이다. The present invention is to determine the weight of the image feature in consideration of the recent user feedback information and the overall feedback information in a system for determining the weight of the image feature (relevance feedback) using the user feedback (relevance feedback) It relates to a method and a method of generating the data feature information. 본 발명은 이미지 검색에 사용되는 특징소들의 가중치를 사용자 피드백에 의해 결정하는 시스템에 있어서, (a). 소정의 이미지에 대한 특징소들을 묘사하는 정보를 가지고, (b). 소정의 이미지에 대한 특징소들의 가중치를 사용자 피드백에 의해서 학습하여 결정할 때 최근의 사용자 피드백 정보를 가지며, (c). 소정의 이미지에 대한 특징소들의 가중치를 사용자 피드백에 의해서 학습하여 결정할 때 지금까지의 전체 피드백 정보를 포함하여, (d). 상기 최근 사용자 피드백 정보와 전체 피드백 정보를 함께 고려하여 이미지 특징소의 가중치를 결정한 후 검색에 이용하도록 한 것을 특징으로 하는 멀티미디어 데이타의 특징소 정보 생성방법과 멀티미디어 데이타의 특징소 가중치 결정방법이다. The present invention provides a system for determining, by user feedback, weights of features used in an image search, comprising: (a). With information depicting features for a given image, (b). Has recent user feedback information when learning and determining weights of the features for a given image by user feedback, (c). Including all feedback information thus far when learning and determining weights of the features for a given image by user feedback, (d). Characteristic information generation method and multimedia element feature determination method of multimedia data, characterized in that the weight of the image feature is determined in consideration of the recent user feedback information and the overall feedback information to be used for the search.