Abstract: The first neural network is a learned neural network learned in such a way as to output, when an object image is input, a geometric transformation parameter relevant to the object image. The object image is an image of an object identified based on object information of the first teaching data including an image and the object information including a category, a position, and a size of an object included in the image. The calculation unit calculates an orientation of the object, based on the geometric transformation parameter being output from the first neural network. The generation unit generates, by adding the orientation of the object being calculated by the calculation unit to the first teaching data, second teaching data including an image and object information including a category, a position, a size, and an orientation of an object included in the image.

Abstract: This application relates to the field of electronic technologies, and provides an action recognition method and apparatus, a terminal device, and a motion monitoring system. Characteristic extraction and action recognition are performed based on motion data collected by data collection apparatuses; a gait characteristic, a swing gesture characteristic, and an image action characteristic of a user are recognized by using a plurality of pieces of motion data; and a type of a hitting action of a player is determined based on the gait characteristic, the swing gesture characteristic, and the image action characteristic. In this way, the hitting action of the player in a motion process can be accurately recognized. This is conducive to performing comprehensive analysis on a comprehensive sports capability of the player, and is more helpful to formulating a personalized training plan for the player.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enhancing biometric authentication are disclosed. According to a method, A circumferential biometric template (CBT) of a particular entity is generated based on one or more images of the particular entity. A request to access an item is received wherein the request includes an identifier corresponding to the particular entity. Circumferential biometric data (CBD) for one or more physical characteristics of an entity depicted in an image captured by an image capture device is obtained, Authentication outcome data indicating whether the CBD matches the CBT of the particular entity is generated. Access to the item is granted when the authentication outcome data indicates that the CBD matches the CBT of the particular entity. Access to the item is denied when the authentication outcome data indicates that the CBD fails to match the CBT of the particular entity.

Abstract: A wine label recognition method, a wine information management method and apparatus, a computer device, and a computer-readable storage medium are provided. The method includes: obtaining a wine image, and performing optical character recognition (OCR) on the wine image in a preset OCR manner, to obtain text included in the wine image (S21); performing deep learning recognition on the wine image in a preset deep learning recognition manner, to obtain an image feature included in the wine image (S22); and sifting out a target wine label matching the text and the image feature from a preset wine label database according to the text and the image feature, and using the target wine label as a wine label corresponding to the wine image (S33). Advantages of deep learning and OCR are fully utilized thereby improving accuracy and efficiency of wine label recognition and improving automation efficiency of wine information management.

Abstract: A video file may be presented via a user application that displays one or more video frames of the video file. A user request to perform an object detection for objects of a specific object type in a video frame of the video file may be received from the user application. A machine-learning model of a plurality of machine-learning models that is configured to detect objects of the specific object type may be applied to the video frame to detect an object of the specific object type in the video frame. Each of the plurality of machine-learning models may be trained to detect objects of a corresponding object type. Subsequently, an object tracking algorithm may be applied to one or more additional video frames of the video file to track the object of the specific object type across the one or more additional video frames.

Abstract: A document capture server receives a document image from a document capture client and processes the image into an electronic document containing textual content. During capture, the document capture server determines a graphical layout of the document, extracts keywords from the document, classifies the document accordingly, and calls an artificial intelligence (AI) platform to gain insights on the textual content. The AI platform analyzes the textual content and returns additional, insightful data such as a sentiment of the textual content. The document capture server can validate the additional data, integrate the additional data in a process or workflow, and/or provide the textual content and the additional data to a content repository or a computing facility operating in an enterprise computing environment. The document capture server can provide validated data to the AI platform to improve future analyses by the AI platform.

Abstract: Various techniques are disclosed to provide for automated verification of the performance of embedded artificial neural networks (ANNs). In one example, a method includes converting a reference ANN to generate an embedded ANN for deployment on an imaging device. The method also includes deploying the reference ANN on a host. The method also includes processing predetermined images by the reference ANN on the host to generate host inference results. The method also includes receiving device inference results from the imaging device at the host in response to processing of the predetermined images by the embedded ANN on the imaging device. The method also includes comparing the device inference results with the host inference results to evaluate performance of the embedded ANN in relation to the reference ANN. Additional methods, devices, and systems are also provided.

Abstract: Methods, systems, and computer-readable media for generating a statistically covaried machine learning model for performance measurement of service providers. The method receives a configuration file that includes one or more parameters associated with a plurality of individuals and parses it to generate and executing the database query on input data to generate sets of tabulated data of individuals of the plurality of individuals. The method next determines one or more measures of service providers listed in the configuration file using two or more tabulated data of individuals from the sets of tabulated data of individuals. The method finally generates a covaried machine learning model by training a machine learning model by statistically covarying measures and using them as training data.

Abstract: A method is proposed for sample processing. A first group of data are received, here data in the first group of data comprises a sample and a classification of the sample, and the classification belonging to a first group of classifications in a plurality of classifications associated with the data. A plurality of data with the classification are selected from the first group of data. A first and a second loss function are determined for training a classification model that represents an association relationship between samples and classifications of the samples based on a plurality of samples comprised in the plurality of data and the classification, the first and second loss functions represent classification accuracy and a feature distribution for the classification model. The classification model is trained based on the first and second loss functions. Therefore, the accuracy of the classification model may be increased.

Abstract: A powder flow monitoring system may include a computing device configured to receive image data representing illuminated powder of a powder stream between a powder delivery device and a build surface of a component, generate a representation of the powder stream based on the image data, and output the representation of the powder stream for display at a display device.

Abstract: A color image inpainting method includes: obtaining a color image of an object to be recognized, the color image including a missing portion where at least part of image information is missing; obtaining an infrared image of the object; identifying the missing portion in the color image; and inpainting the missing portion in the color image identified in the identifying. The inpainting includes inpainting the missing portion by using information which is obtained from the infrared image and corresponds to the missing portion to obtain an inpainted color image of the object.

Abstract: Embodiments of the present disclosure provide a method, an electronic device, and a computer program product for evaluating samples. The method includes receiving, at an edge device, a classification model from a cloud server. The method further includes acquiring a sample distribution corresponding to each class in a plurality of classes of the classification model. The method further includes acquiring an input sample which is marked as a first class in the plurality of classes. The method further includes determining whether the input sample conforms to a first sample distribution corresponding to the first class. The method further includes identifying, in response to the input sample conforming to the first sample distribution, the input sample as a trusted sample. The trusted sample indicates that the input sample is correctly marked. By the method, a noise sample with a wrong label can be recognized, thus avoiding model degradation during update.

Abstract: An image processing device includes a three-dimensional noise reduction (3D NR) circuit, an artificial intelligence noise reduction (AI NR) circuit, a weight determination circuit and an image blending circuit. The 3D NR circuit performs a 3D NR operation on input image data to generate first image data. The AI NR circuit performs an AI NR operation on the input image data to generate second image data. The weight determination circuit outputs a blending weight according to a motion index. The image blending circuit blends the first image data and the second image data according to the blending weight to generate output image data.

Abstract: A powder flow monitoring system may include a computing device configured to receive image data representing illuminated powder of a powder stream between a powder delivery device and a build surface of a component, generate a representation of the powder stream based on the image data, and output the representation of the powder stream for display at a display device.

Abstract: Disclosed herein is a method for encoding a feature map. The method may include arranging multiple channels based on similarity therebetween for a feature map having the multiple channels, rearranging the arranged multiple channels so as to be adjacent to each other in a feature map channel having a matrix form, and generating an encoded feature map by converting a feature value corresponding to the feature map channel from a real number to an integer.

Abstract: Methods, apparatus, and processor-readable storage media for automated image analysis using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining image data associated with at least one event; characterizing a plurality of attributes of the image data by processing at least a portion of the image data using one or more artificial intelligence techniques and processing metadata associated with at least a portion of the image data using one or more rule-based techniques; generating a determination as to whether one or more portions of the image data have been modified based at least in part on the plurality of characterized attributes of the image data; and performing one or more automated actions, based at least in part on the determination, in connection with at least one user request related to the image data associated with the at least one event.

Abstract: Provided is a method for providing annotation information for a 3D image, which may include outputting a representative image for the 3D image including a plurality of slices, selecting at least one pixel associated with a target item from among a plurality of pixels included in the representative image, outputting, among the plurality of slices, a slice associated with the selected at least one pixel, and receiving an annotation for a partial region of the output slice.

Abstract: A system including a light source that, in operation, projects dots onto a target, the dots being formed by first light; a first photodetector that, in operation, detects second light resulting from the projection of the dots onto the target; and a circuit that in operation, performs an individual authentication, wherein the individual authentication includes at least the following step (i) and step (ii): step (i) determining whether the target is a living body or not based on the second light, and step (ii) performing a biometric authentication of the target.

Abstract: A system (IPS) and related method for image processing, in particular dark-field or phase contrast imaging to reduce motion artifacts. The system comprises an input interface (IN) for receiving a series of projection images (?) acquired by an X-ray imaging apparatus (XI) of an object (OB) for a given projection direction, the imaging apparatus (XI) configured for phase-contrast and/or dark-field imaging A phase-contrast and/or dark-field image generator (IGEN) applies an image generation algorithm to compute a first image based on the series the projection images (?). A motion artifact detector (MD) detects a motion artifact in the first image. A combiner (?) combines, if a motion artifact is so detected, a part of the first image with a part of at least one auxiliary image to obtain a combined image. The auxiliary image was previously computed by a gated application of the image generation algorithm in respect of a subset of the series of the projection images (?).

Abstract: The present disclosure provides a system and method for image data acquisition. The method may include obtaining image data of a subject including a first type of tissue and a second type of tissue. The method may include determining, based on the image data of the subject, a target portion including at least a portion of at least one of the first type of tissue or the second type of tissue. The method may include determining, based at least in part on the target portion represented in the image data, a scan mode corresponding to the target portion. The method may include causing an imaging device to acquire, based on the scan mode, image data of the target portion.