A system, method, and computer program product for implementing video action recognition is provided. The method includes receiving a video stream comprising user movement actions. Skeleton points associated with a video representation of a user executing the user movement actions are extracted and categorized with respect to multiple digital levels. Initial visual windows points are generated within video frames and an average movement distance for the group of skeleton points are determined with respect to the video frames. In response, sizes for the visual windows are adjusted and feature vectors are extracted from the group of skeleton points. Point coordinates of the skeleton points are extracted and linked with the feature vectors. A convolutional neural network associated with linking the feature vectors with the point coordinates is generated and the video stream is enabled with respect to video action recognition associated with accurate presentation of the video stream.

A Shape Based Modeling Segmentation fits generated Bézier curves on to edges parsed from an object in an image, identifies the Bézier curves in predefined proximity having at least one of a geometric relationship and a reporting relationship with other Bézier curves in the predefined proximity; generates MetaBézier curves from the identified Bézier curves; and connects the MetaBézier curves to identify the object in the image.

The invention provides a method and a device for identifying the number of bills and multiple bill areas in an image. The method comprises the following steps: acquiring the image containing a plurality of bills arranged in sequence; processing the image to obtain a plurality of boundary lines of each bill in the image; wherein the boundary lines comprise a first type of boundary lines which are substantially perpendicular to the bill arrangement direction; generating a long line segment which is substantially parallel to the arrangement direction of the bills and passes through the area where all the bills are located, wherein the long line segment has an intersection point with each first type of boundary line; and determining the number of bills in the image according to the lengths of the sub-line segments between the adjacent intersection points.

A method, performed by a processor, for processing a blood vessel image from an angiography image may comprise the steps of: extracting a target blood vessel from a blood vessel image; identifying an error portion from the extraction result of the target blood vessel on the basis of at least one of blood vessel structure data related to the target blood vessel, curvature information of the target blood vessel, diameter information of the target blood vessel, and brightness information of the target blood vessel; and in response to a case where an error portion is identified in the target blood vessel, correcting the identified error portion.

A computerized method of providing automatic anatomy recognition (AAR) includes gathering image data from patient image sets, formulating precise definitions of each body region and organ and delineating them following the definitions, building hierarchical fuzzy anatomy models of organs for each body region, recognizing and locating organs in given images by employing the hierarchical models, and delineating the organs following the hierarchy. The method may be applied, for example, to body regions including the thorax, abdomen and neck regions to identify organs.

A non-transitory computer-readable recording medium stores an information processing program for causing a computer to execute processing including: acquiring data that indicates a relationship between element actions for a plurality of element actions in an object period; acquiring an effective time that corresponds to an object action; and searching for a combination of two or more element actions that form the object action among the plurality of element actions for each divided section set by dividing the object period according to the acquired effective time on the basis of the acquired data.

A connected component analysis (CCA) method, which can use labels repeatedly, comprising: defining a label pattern comprising a label and a plurality of neighboring labels; setting a center label of a current pixel of a target binary image according to a binary value of the current pixel and the neighboring pixels; setting at least two of the neighboring labels according to whether the current pixel is in any one of a first row, a first column and a last column; and recording the center label to a label buffer. Labels for marking pixels of the target binary image are first center labels, and then are second center labels, and are the first center labels again after the labels are the second center labels.

Systems and methods for detecting anomalies in aviation data communication systems (e.g., air traffic control surveillance systems), include a processor receiving device status information. A variational autoencoder receives and optimizes the device status information and determines whether it qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

A method of the disclosure includes receiving, by a processing device, a document image, dividing the document image into a plurality of patches and determining, for each patch, whether the patch is monochromatic or polychromatic. It further includes clusterizing a plurality of monochromatic patches into a plurality of clusters within a color space, wherein each cluster corresponds to a color layer of a plurality of color layers of the document image, and segmenting each polychromatic patch into a corresponding plurality of monochromatic segments. The method also includes, for each polychromatic patch, associating each monochromatic segment of the corresponding plurality of monochromatic segments with a cluster of the plurality of clusters, and utilizing the plurality of clusters for performing an information extraction task on the document image.

In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.