Abstract: Image-based key points detection using a convolutional neural network (CNN) may be impacted if the key points are occluded in the image. Images obtained from additional imaging modalities such as depth and/or thermal images may be used in conjunction with RGB images to reduce or minimize the impact of the occlusion. The additional images may be used to determine adjustment values that are then applied to the weights of the CNN so that the convolution operations may be performed in a modality aware manner to increase the robustness, accuracy, and efficiency of key point detection.

Abstract: Embodiments of the present disclosure relate to a method, an electronic device, and a computer program product for data augmentation. The method includes: generating a group of candidate images based on a target image by using a thermodynamic genetic algorithm (TDGA) model, the TDGA model being configured to apply one or more operations of a set of predetermined image processing operations during each evolution process; and determining multiple augmented images from the group of candidate images based on free energy of the group of candidate images, the multiple augmented images being determined as belonging to the same classification with the target image. In this way, data augmentation can be efficiently implemented by a thermodynamic genetic algorithm.

Abstract: A method for obtaining and processing image data by using a medical visual aid system including a monitor and an endoscope configured to be inserted into a body cavity and including an image capturing device and a light emitting device, the method including illuminating a field of view of the image capturing device with the light emitting device, capturing the image data using the image capturing device, providing a non-linear scaling model adapted to the body cavity, adjusting the image data by applying the non-linear scaling model such that adjusted image data is formed, and presenting the adjusted image data on the monitor.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a final progression score characterizing a likelihood that a state of a medical condition affecting eye tissue will progress to a target state in a future interval of time. In one aspect, a method comprises: obtaining: (i) an input image of eye tissue captured using an imaging modality, and (ii) a segmentation map of the eye tissue in the input image into a plurality of tissue types; providing the input image to each of one or more first classification neural networks to obtain a respective first progression score from each first classification neural network; providing the segmentation map to each of one or more second classification neural networks to obtain a respective second progression score from each second classification neural network; and generating the final progression score based on the first and second progression scores.

Abstract: In an example method of training a neural network for performing visual odometry, the neural network receives a plurality of images of an environment, determines, for each image, a respective set of interest points and a respective descriptor, and determines a correspondence between the plurality of images. Determining the correspondence includes determining one or point correspondences between the sets of interest points, and determining a set of candidate interest points based on the one or more point correspondences, each candidate interest point indicating a respective feature in the environment in three-dimensional space). The neural network determines, for each candidate interest point, a respective stability metric and a respective stability metric. The neural network is modified based on the one or more candidate interest points.

Abstract: Embodiments of the disclosure are directed to methods and systems for creating a medical image database, wherein data which comprise partial images of two-dimensional or higher-dimensional initial images of parts of the human body are created, a projection for obtaining feature vectors is created from the partial images, wherein, in order to prepare the execution of the projection, a neural network based on specified learning partial images is created, wherein the data records are used within the scope of a metric learning method to learn the projection and creation of the feature vectors from learning partial images. This is achieved for example by specifying learning partial images that are slightly shifted, rotated, skewed or stretched relative to one another and were created starting from the same initial image as similar.

Abstract: Disclosed are an image processing method and device, a training method of a neural network and a storage medium. The image processing method includes: obtaining an input image, and processing the input image by using a generative network to generate an output image. The generate network includes a first sub-network and at least one second sub-network, and the processing the input image by using the generative network to generate the output image includes, processing the input image by using the first sub-network to obtain a plurality of first feature images; performing a branching process and a weight sharing process on the plurality of first feature images by using the at least one second sub-network to obtain a plurality of second feature images; and processing the plurality of second feature images to obtain the output image.

Abstract: A nail application causes an information processing apparatus to function as a user information input unit that acquires user information, an image display control unit that acquires image data of a finger inclusive of a nail of a user, and a nail detection unit that detects a nail area based on data indicating the nail area in the image data to be outputted from a nail detection model as a consequence of inputting the image data and the user information to the nail detection model.

Abstract: A server includes a control unit. The control unit determines whether a parked vehicle is used as a shelter based on a first image which is included in an image captured by a camera and which is obtained by imaging the vehicle and surroundings of the vehicle.

Abstract: Provided is a method for generating an image label, including: acquiring a partial image of a target image after acquiring the target image with a label to be generated; then, acquiring a plurality of features based on the target image and the partial image, wherein the plurality of features include a first feature of the target image and a second feature of the partial image; and finally, generating a first-type image label of the target image based on the first feature and the second feature.

Abstract: A computer model is trained to classify regions of a space (e.g., a pixel of an image or a voxel of a point cloud) according to a multi-label classification. To improve the model's accuracy, the model's self-confidence is determined with respect to its own predictions of regions in a training space. The self-confidence is determined based on the class predictions, such as a difference between the highest-predicted class and a second-highest-predicted class. When these are similar, it may reflect areas for potential improvement by focusing training on these low-confidence areas. Additional training may be performed by including modified training data in subsequent training iterations that focuses on low-confidence areas. As another example, additional training may be performed using the self-confidence to modify a classification loss used to refine parameters of the model.

Abstract: A system for identifying melanoma and other skin cancer in a dermoscopy image comprises: an image analyzer having at least one processor that instantiates at least one component stored in a memory, the at least one component comprising: a segmenter configured to segment a lesion from the rest of the image, a handcrafted feature component including: a median color splitting model for separating the image into a plurality of color regions, a vessel detection model for detecting elevated vascularity, an atypical pigment network detection model for identifying a pigment network whose structure varies in size and shape, a salient point detection model for detecting salient points based on an intensity plane of the image, a color detection model for detecting at least one of a white area, a pink shade, a pink blush, and a semi-translucency, a hair detection model for characterizing detected hairs and ruler marks, an outside model that finds the above model features on non-dark-corner areas outside the segmented are

Abstract: A data partitioning system receives an input dataset for e-commerce products, each sample containing attributes and associated values for each product including at least an image; represents each sample as a node on a graph to provide a graph of nodes for the dataset; measures a relative similarity distance between each pair of nodes based on comparing at least image values for the attributes; determines for each pair of nodes whether they are related if the similarity distance between them is below a defined threshold, and if related, generate an edge between them on the graph; group the connected nodes into a first or a second group such that the grouped nodes have no edges connecting them to nodes in the other group and have a shortest relative similarity distance with each other. The groups are used as training dataset and testing data sets for a supervised machine learning classifier.

Abstract: A method for detecting and dimensioning a target object includes: obtaining depth data representing a target object; defining a mask having a structure which decreases in density away from a central point of the mask; overlaying the mask on the depth data and selecting a subset of the depth data comprising data points which contact the mask; detecting a cluster of data points from the subset; detecting, based on the cluster, the target object; and outputting a representation of the target object.

Abstract: A data processing system for generating a fingerprint of an image implements obtaining a first digital image; determining a first fingerprint for the first digital image comprising a first coarse-grain fingerprint element and a first fine-grain fingerprint element by determining the first coarse-grain component based on the first digital image; determining the first fine-grain component based on the first digital image; and generating the first fingerprint by combining the first coarse-grain component with the first-fine grain component; obtaining a second fingerprint for a second digital image, the second fingerprint comprising a second coarse-grain component and a second fine-grain component; comparing the first fingerprint with the second fingerprint to determine a similarity score; and performing one or more actions responsive to the similarity score equaling or exceeding a similarity threshold.

Abstract: A CPU acquires a radiographic image obtained by imaging an imaging region where a patient is present, with a radioscopy apparatus using radiation emitted from a radiation source and applied to an irradiation field adjusted by a collimator. The CPU specifies a structure image that is included in the radiographic image and represents a structure of a specific shape having transmittance of radiation lower than the patient, based on the specific shape. The CPU executes image processing corresponding to the structure image on a patient image region imaged by a radioscopy apparatus in a case where an irradiation field excluding a position of the structure is set as the irradiation field, in a region in the radiographic image.

Abstract: Described herein are systems and methods for determining if a vehicle is parked. In one example, a system includes a processor, a sensor system, and a memory. Both the sensor system and the memory are in communication with the processor. The memory includes a parking determination module having instructions that, when executed by the processor, cause the processor to determine, using a random forest model, when the vehicle is parked based on vehicle estimated features, vehicle learned features, and vehicle taillight features of the vehicle that are based on sensor data from the sensor system.

Abstract: Provided is a method for improving reliability of artificial intelligence-based object recognition, in which: in a server interworking with an artificial intelligence module, one or more object regions included in learning data including an image of a recognition target object to be recognized through the artificial intelligence module are recognized; object region recognition data which sets the recognized object regions is extracted and is provided to user terminals in a designated order; a procedure for receiving, from the user terminals, object region selection data which selects at least one effective object region corresponding to the recognition target object among object regions included in the object region recognition data is performed; and the object region selection data of respective users received from the user terminals is mutually compared and analyzed by the same object region selection data.

Abstract: Embodiments of the present disclosure provide an image recognition method and apparatus, an electronic device and a medium, and relates to the field of image processing. The method may include: acquiring a to-be-recognized image sent by a client, and determining whether the to-be-recognized image is a back image; determining characteristic information of the to-be-recognized image in at least one dimension, when it is determined that the to-be-recognized image is the back image; and determining a target front side image matching the to-be-recognized image according to the characteristic information, and returning the target front side image to the client to cause the client to display the target front side image.

Abstract: A system and a method for determining an object has been on a vehicle seat of a vehicle are provided. The processing circuitry may determine if passengers of the vehicle have left the vehicle. The processing circuitry may determine if a temperature of a vehicle cabin of the vehicle meets a threshold of temperature. The temperature of the vehicle cabin to a first temperature may be adjusted. A temperature of resistive filaments of the vehicle seat of the vehicle to a second temperature may be adjusted. A thermal image of the vehicle seat with a reference thermal image of the vehicle seat may be compared. The processing circuitry may determine if the object has been left on the vehicle seat.