Abstract: Provided are a communication link adjustment method and apparatus, an electronic device, and a readable medium. The method includes that: interference information of a communication link under a multi-connection scenario is acquired; whether an isolation degree value of the communication link exceeds a range defined by a preset isolation degree threshold is determined according to the interference information; and in a case where the isolation degree value of the communication link exceeds the range defined by the preset isolation degree threshold, the communication link is adaptively adjusted according to the isolation degree value and an isolation degree adjustment mapping table until the isolation degree value meets a requirement for a wireless performance index, wherein the isolation degree adjustment mapping table includes a mapping relationship between isolation degree values and path parameters.

Abstract: In some embodiments, a system is provided that includes an edge computing device and at least one camera configured to obtain image data depicting at least a portion of an operations area. The edge computing device includes a non-transitory computer-readable medium that has a model data store and computer-executable instructions stored thereon. The instructions cause the edge computing device to perform actions including receiving at least one image from the at least one camera; processing the at least one image using at least one machine learning model stored in the model data store to determine at least one environmental state within the operations area; and controlling a device based on the determined at least one environmental state. The machine learning model is trained by a model management computing system that obtains training data via low-bandwidth connections to edge computing devices.

Abstract: Systems and methods are disclosed for generating synthetic medical images, including images presenting rare conditions or morphologies for which sufficient data may be unavailable. In one aspect, style transfer methods may be used. For example, a target medical image, a segmentation mask identifying style(s) to be transferred to area(s) of the target, and source medical image(s) including the style(s) may be received. Using the mask, the target may be divided into tile(s) corresponding to the area(s) and input to a trained machine learning system. For each tile, gradients associated with a content and style of the tile may be output by the system. Pixel(s) of at least one tile of the target may be altered based on the gradients to maintain content of the target while transferring the style(s) of the source(s) to the target. The synthetic medical image may be generated from the target based on the altering.

Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

Abstract: An apparatus (1), for use in conjunction with a medical imaging device (2) having an imaging device controller (4) that displays a graphical user interface (GUI) (8) including a preview image viewport (9), includes at least one electronic processor (20) programmed to: perform an image analysis (38) on a preview image displayed in the preview image viewport to generate preview-derived image label information; extract GUI-derived image label information from the GUI excluding the preview image displayed in the preview image viewport; and output an alert (30) when the preview-derived image label information and the GUI-derived image label information are not consistent.

Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory that is shared by all neural networks; providing a local memory for each neural network, respectively; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory and/or into the local memory, and/or reading out data from this shared memory and/or local memory and further processing the data by the neural network.

Abstract: A facial expression recognition method includes extracting a first feature from color information of pixels in a first image, and extracting a second feature of facial key points from the first image. The method further includes combining the first feature and the second feature, to obtain a fused feature, and determining, by processing circuitry of an electronic device, a first expression.

Abstract: A method and system for fish identification based on body surface texture features and geometric features are provided. The method employs an improved Resnet network and a deep learning Yolov8 network to extract body surface texture features and geometric features of a fish on the basis of considering influences of fish tail swing and an oxygen concentration on a fish body form based on a small sample learning framework, and then realizes identity recognition of a fish individual by coupled analysis of the body surface texture features and the geometric features. The method can realize high-accuracy fish identification with few training samples of a fish to be identified from the perspective of actual application, provides theoretical basis and technical support for accurate fish stock assessment and accurate estimation of industrially farmed fish biomass, and meets the development requirements of modern agriculture.

Abstract: Methods, systems, and apparatus for training a graph neural network. An example method includes obtaining a complete graph; dividing the complete graph into a plurality of subgraphs; obtaining a training graph to participate in graph neural network training based on selecting at least one subgraph from the plurality of subgraphs; obtaining, based on the training graph, a node feature vector of each node in the training graph; obtaining a node fusion vector of each current node in the training graph; determining a loss function based on node labels and the node fusion vectors in the training graph; and iteratively training the graph neural network to update parameter values of the graph neural network based on optimizing the loss function.

Abstract: The present disclosure relates generally to image processing, and more particularly, toward techniques for structured illumination and reconstruction of three-dimensional (3D) images. Disclosed herein is a method to jointly learn structured illumination and reconstruction, parameterized by a diffractive optical element and a neural network in an end-to-end fashion. The disclosed approach has a differentiable image formation model for active stereo, relying on both wave and geometric optics, and a trinocular reconstruction network. The jointly optimized pattern, dubbed “Polka Lines,” together with the reconstruction network, makes accurate active-stereo depth estimates across imaging conditions. The disclosed method is validated in simulation and used with an experimental prototype, and several variants of the Polka Lines patterns specialized to the illumination conditions are demonstrated.

Abstract: According to one embodiment, an anomaly detection device includes a processor that is configured to acquire input data. The processor derives a first anomaly degree corresponding to a difference between first feature data derived from the input data using a trained deep model and second feature data derived from the input data using a trained prediction model. The processor derives a second anomaly degree corresponding to an estimated relative positional relationship between a first and second region in the image data based on the second feature data. A total anomaly degree for the input data is then calculated from the first anomaly degree and the second anomaly degree.

Abstract: Systems and methods for image dense field based view calibration are provided. In one embodiment, an input image is applied to a dense field machine learning model that generates a vertical vector dense field (VVF) and a latitude dense field (LDF) from the input image. The VVF comprises a vertical vector of a projected vanishing point direction for each of the pixels of the input image. The latitude dense field (LDF) comprises a projected latitude value for the pixels of the input image. A dense field map for the input image comprising the VVF and the LDF can be directly or indirectly used for a variety of image processing manipulations. The VVF and LDF can be optionally used to derive traditional camera calibration parameters from uncontrolled images that have undergone undocumented or unknown manipulations.

Abstract: The technology disclosed introduces two types of neural networks: “master” or “generalists” networks and “expert” or “specialists” networks. Both, master networks and expert networks, are fully connected neural networks that take a feature vector of an input hand image and produce a prediction of the hand pose. Master networks and expert networks differ from each other based on the data on which they are trained. In particular, master networks are trained on the entire data set. In contrast, expert networks are trained only on a subset of the entire dataset. In regards to the hand poses, master networks are trained on the input image data representing all available hand poses comprising the training data (including both real and simulated hand images).

Abstract: Provided are an electronic device for sharpening an image and an operation method thereof. A method, performed by the electronic device, of sharpening an image includes: obtaining an image generated by a camera of the electronic device; obtaining a first sharpening kernel for enhancing sharpness of the image, wherein the first sharpening kernel is data including a plurality of weights to be applied to pixels in the image, the data being of a lower resolution than the image; determining coordinates corresponding to some weights indicating representative values of the first sharpening kernel from among the plurality of weights in the first sharpening kernel; generating a second sharpening kernel by selecting the weights corresponding to the determined coordinates; and obtaining a sharpened image by applying the second sharpening kernel to the image.

Abstract: A system and method configured to better identify patient-specific anatomical landmarks, measure anatomical parameters and features, and predict the patient's need for surgery within a predetermined time period. In some embodiments, the system and method is configured to predict the likelihood or risk that a patient will require total hip arthroplasty. In some embodiments, the present invention includes machine learning technology Some embodiments of the present invention include a first ML machine configured to received medical images as inputs and identify anatomical landmarks as outputs; a measurement module to measure joint space width, hip dysplasia angles, and/or leg length differential; and a second ML machine configured to receive the anatomical measurements and patient demographic data as inputs and produce a risk or likelihood that the patient will require surgery within a certain time frame.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for processing an image using visual and textual information. An example apparatus includes at least one memory, instructions in the apparatus, and processor circuitry to execute the instructions to detect regions of interest corresponding to a product promotion of an input digital leaflet, extract textual features from the product promotion by applying an optical character recognition (OCR) algorithm to the product promotion and associating output text data with corresponding ones of the regions of interest, determine a search attribute corresponding to the product promotion, generate a first dataset of candidate products corresponding to the product in the product promotion by comparing the search attribute against a second dataset of products, and select a product from the first dataset of candidate products to associate with the product promotion, the product selected based on a match determination.

Abstract: Disclosed herein is a method of automatically obtaining training images to train a machine learning model that improves image quality. The method may comprise analyzing a plurality of patterns of data relating to a layout of a product to identify a plurality of training locations on a sample of the product to use in relation to training the machine learning model. The method may comprise obtaining a first image having a first quality for each of the plurality of training locations, and obtaining a second image having a second quality for each of the plurality of training locations, the second quality being higher than the first quality. The method may comprise using the first image and the second image to train the machine learning model.

Abstract: The learning device includes: a first estimation unit configured to perform estimation using a temperature parameter, based on a student model; a second estimation unit configured to perform estimation using the temperature parameter, based on a teacher model; and a temperature calculation unit configured to calculate the temperature parameter, based on estimation information generated by the first estimation unit and the second estimation unit.

Abstract: Various implementations disclosed herein include devices, systems, and methods that determine a wrist measurement or watch band size using depth data captured by a depth sensor from one or more rotational orientations of the wrist. In some implementations, depth data captured by a depth sensor including at least two depth map images of a wrist from different angles is obtained. In some implementations, an output is generated based on inputting the depth data into a machine learning model, the output corresponding to circumference of the wrist or a watch band size of the wrist. Then, a watch band size recommendation is provided based on the output.

Abstract: A computer-implemented method of an embodiment is for automatically estimating and/or correcting an error due to artifacts in a multi-energy computed tomography result dataset relating to at least one target material. In an embodiment, the method includes determining at least one first subregion of the imaging region, which is free from the target material and contains at least one, in particular exactly one, second material with known material-specific energy dependence of x-ray attenuation; for each first subregion, comparing the image values of the energy dataset for each voxel, taking into account the known energy dependence, to determine deviation values indicative of artifacts; and for at least a part of the at least one remaining second subregion of the imaging region, calculating estimated deviation values by interpolating and/or extrapolating from the determined deviation values in the first subregion, the estimated deviation values being used as estimated error due to artifacts.