In an image comparison method, an original reference image and an original test image are obtained. The original reference image and the original test image are binarized to obtain a reference binary image and a test binary image. The reference binary image and the test binary image are detected edges to obtain a reference edge image and a test edge image. A morphological expansion is performed on the reference edge image to obtain an expanded reference edge image. An OR operation is performed on the extended reference edge image and the test edge image to obtain an extended test edge image. An XOR operation is performed on the expanded reference edge image and the expanded test edge image. The method improves the accuracy of image comparison.

A method for dynamically measuring deformation of a rotating-body mold, including: (S1) subjecting an overall outer surface of the rotating-body mold to three-dimensional measurement to acquire an initial point cloud data; (S2) shooting, by a multi-camera system, the mold from different angles to obtain three-dimensional coordinates of marking points and coding points on the overall outer surface of the rotating-body mold; (S3) rotating the mold, and repeatedly photographing the marking points and the coding points on the mold surface under different angle poses; and calculating three-dimensional coordinates of the marking points and the coding points; and (S4) predicting a point cloud data of the outer surface under different angle poses based on a conversion relationship among the marking points to analyze a deformation degree of the mold during a rotation process.

Embodiments of the present disclosure disclose image processing methods and apparatuses, image devices, and storage media. The image processing method includes: obtaining an image; obtaining the feature of the limb of the body based on the image, where the limb includes the upper limb and/or the lower limb; determining first-type movement information of the limb based on the feature; and controlling the movement of the limb of a controlled model according to the first-type movement information.

A vision guided intelligent system for automated crab meat picking operates in a fully automated or semi-automatic modes of operation using a crab meat picking routine based on (a) the CNN model localization of back-fin knuckles algorithm, and/or (b) the Deep Learning model which accurately locates not only knuckle positions, but also crab legs and crab cores, with a high pixel accuracy (up to 0.9843), and low computation time. The subject system uses a concept of analyzing crab morphologies obtained from digital crab images, and, using a Deep Learning architecture integrated in the system, segments crab images into five regions of interest in a single step with high accuracy and efficiency. The image segmentation results are used for generating crab cut lines in XYZ and angular directions, determining starting cutting points in Z plane, and guiding cutting tools and end effectors to automatically cut crabs and harvest crab meat.

Devices, systems, computer program products and computer implemented methods are provided for dynamically assessing a moving object from a sequence of consecutive volumetric image frames of such object, which images are timely separated by a certain time interval, by: identifying in at least one image of the sequence the object of interest; segmenting the object to identify object contour; propagating the object contour as identified to other images of the sequence; and performing dynamic analysis of the object based on the object contour as propagated.

An acquired image is analysed to determine a test outcome value. A shape template for a test structure is provided to identify a position of a target measurement region on the test structure. A mapping defining a transformation of the shape template onto the image frame is determined. A mapping is determined and it is determined if a first matching condition based on first displacements of one or more edges identified in the image frame relative to the shape template is satisfied for the mapping. When the mapping satisfies the first matching condition and a second different matching condition based on second displacements of one or more edges identified in the image frame relative to the shape template, a verified image of a test structure is established. In the verified image of the test structure a target measurement region is identified. A test outcome value is determined by analysing the target measurement region.

Provided is a system and method for estimating the motion of a target inside a tissue based on surface deformation of the soft tissue. The system consists of an acquisition unit, a reference input unit, two surface extraction units, a target position extraction unit, a feature calculation unit, and a target motion estimation unit. The method includes: the acquisition unit acquires an image I.sub.i of the soft tissue; the surface extraction unit extracts a surface f.sub.i of the soft tissue from I.sub.i; the reference input unit acquires a reference image I.sub.ref of the soft tissue; the surface extraction unit and the target position extraction unit respectively extract a reference surface f.sub.ref of the soft tissue and a target reference position t.sub.ref from I.sub.ref, the feature calculation unit calculates deformation feature Ψ.sub.i of f.sub.i relative to f.sub.ref, the target motion estimation unit estimates the target displacement based on Ψ.sub.i and t.sub.ref.

An image modification system receives image features of a base image and an additional image. The base image and the additional image depict an apparel item displayed on a mannequin. A first feature pair from the base image and a second feature pair from the additional images are determined. A first distance is calculated between the first feature pair and a second distance is calculated between the second feature pair. Based on a ratio including the first and second distances, a matching relationship between the first and second feature pairs is determined. A pixel of the base image is identified within an image area occluded by the mannequin. Based on the matching relationship, image data is identified for a corresponding additional pixel from the additional image. A modified base image including a ghost mannequin effect is generated by modifying the pixel to include the image data of the additional pixel.

Systems, computer program products, and methods are described herein for real-time imitation network generation using artificial intelligence. The present invention is configured to electronically receive, from a computing device of a user, a real dataset; initiate one or more machine learning algorithms on the real dataset; determine, using the one or more machine learning algorithms, one or more data distribution parameters associated with the real dataset; electronically receive, from the computing device of the user, a first shift parameter; skew the one or more data distribution parameters using the first shift parameter to generate one or more skewed data distribution parameters; and generate, using the one or more machine learning algorithms, an imitation dataset using the one or more skewed data distribution parameters.

Device, system, and method of generating a reduced-size volumetric dataset. A method includes receiving a plurality of three-dimensional volumetric datasets that correspond to a particular object; and generating, from that plurality of three-dimensional volumetric datasets, a single uniform mesh dataset that corresponds to that particular object. The size of that single uniform mesh dataset is less than ¼ of the aggregate size of the plurality of three-dimensional volumetric datasets. The resulting uniform mesh is temporally coherent, and can be used for animating that object, as well as for introducing modifications to that object or to clothing or garments worn by that object.