The present disclosure provides an image-viewing method, a terminal, and a cleaner.

Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.

A system for estimating a pose of one or more persons in a scene includes a camera configured to capture one or more images of the scene; and a data processor configured to execute computer executable instructions for: (i) receiving the one or more images of the scene from the camera; (ii) extracting features from the one or more images of the scene for providing inputs to a keypoint subnet and a person detection subnet; (iii) generating one or more keypoints using the keypoint subnet; (iv) generating one or more person instances using the person detection subnet; (v) assigning the one or more keypoints to the one or more person instances by learning pose structures from image data; and (vi) determining one or more poses of the one or more persons in the scene using the assignment of the one or more keypoints to the one or more person instances.

In one aspect, an example method for generating a candidate image for use as backdrop imagery for a graphical user interface is disclosed. The method includes receiving a raw image and determining an edge image from the raw image using edge detection. The method also includes identifying a candidate region of interest (ROI) in the raw image based on the candidate ROI enclosing a portion of the edge image having edge densities exceeding a threshold edge density. The method also includes manipulating the raw image relative to a backdrop imagery canvas for a graphical user interface based on a location of the candidate ROI within the raw image. The method also includes generating, based on the manipulating, a set of candidate backdrop images in which at least a portion of the candidate ROI occupies a preselected area of the backdrop imagery canvas, and storing the set of candidate backdrop images.

A document reading device includes a document conveyer, a first reader reading, in a first reading position, a first surface of a conveyed document such that a read area is larger than the conveyed document, a second reader reading, in a second reading position, a surface (second surface) opposite to the first surface such that a read area is larger than the conveyed document, a region detector executing a process of detecting a first document region that is a region of a document in first document image data and a process of detecting a second document region that is a region of the document in second document image data, and a cropping processor cropping a document portion on the first surface as first cropped image data and cropping a document portion on the second surface as second cropped image data, based on one of the document regions successfully detected.

A method and an apparatus of transferring an image, a method of training an image transfer model, a device, and a medium. The method of transferring the image includes: extracting a first attribute feature of a first object and a first shape feature of a target part of the first object respectively according to a first image and a first position information of the target part of the first object in the first image; extracting a first identity feature of a second object contained in a second image; and generating a first transferred image according to the first attribute feature, the first shape feature and the first identity feature, wherein the first transferred image contains the second object having the first attribute feature and the first shape feature.

A method of detecting a cart-based loss incident in a retail store includes decoding one or more video frames of a video stream to obtain one or more motion vectors therefrom, detecting motion of a shopping cart within a cash register lane bounded by pre-defined tracking start and end points based on the one or more motion vectors, tracking a location of the shopping cart till the shopping cart reaches the pre-defined tracking end point, dynamically classifying the shopping cart in one of a plurality of classification statuses based on recognition of one or more items present in the shopping cart till the shopping cart reaches the pre-defined tracking end point, and generating an alert signal when the shopping cart is classified in a pre-defined classification status from the plurality of classification statuses at an alert threshold point between the pre-defined tracking start and end points.

Techniques are described for learning feature representations of medical images using a self-supervised learning paradigm and employing those feature representations for automating downstream tasks such as image retrieval, image classification and other medical image processing tasks. According to an embodiment, computer-implemented method comprises generating alternate view images for respective medical images included in set of training images using one or more image augmentation techniques or one or more image selection techniques tailored based on domain knowledge associated with the respective medical images. The method further comprises training a transformer network to learn reference feature representations for the respective medical images using their alternate view images and a self-supervised training process. The method further comprises storing the reference feature representations in an indexed data structure with information identifying the respective medical images that correspond to the reference feature representations.

A system and method for animal disease management is disclosed. The method includes receiving one or more images, one or more videos of one or more animals or a combination thereof and identifying one or more faces of the one or more animals in the one or more images, the one or more videos of one or more animals or a combination thereof. The method further includes extracting one or more facial features and one more muzzle features from the one or more faces and determining one or more facial changes and one or more muzzle changes. The method includes detecting presence or absence of one or more diseases in the one or more animals, predicting likelihood of the one or more diseases or a combination thereof based on the one or more facial changes, the one or more muzzle changes and the predefined information.

A pallet inspection system includes a frame configured to have a pallet receiving area to receive a wooden pallet to be inspected for having at least one mark indicating that wood in the pallet has been heat treated. Cameras are carried by the frame to generate images of the wooden pallet in response to the wooden pallet being in the pallet receiving area. A processor is to perform object detection on each image to detect if the mark is present, crop each image having the mark so that an area surrounding the mark within the image is removed, and perform image segmentation on each cropped image so that pixels within the cropped image are classified into regions. The processor determines readability of the regions in each cropped image based on respective readability criteria thresholds. The mark is classified in each cropped image as readable based on the mark meeting the respective readability criteria thresholds.