A method for creating a machine learning system, which is configured for segmentation and object detection. The method includes: providing a directed graph, selecting a path through the graph, at least one additional node being selected from a subset and a path being selected through the graph from the input node along the edges via the additional node up to the output node, the path initially being drawn as a function of probabilities of the edges, which defines a drawing probability of all architectures within the graph, creating a machine learning system as a function of the selected path and training the created machine learning system.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to train a generative adversarial network (GAN) to reconstruct a missing portion of an image by determining a reconstructed portion of the image based on data from portions of the image surrounding the missing portion and compare an acquired image with the reconstructed portion of the image to determine a damaged portion. The instructions further include instructions to determine estimated damage based on the damaged portion.

A method for extracting sentiments or mood from art images includes: receiving at least one of the art images as an input image; preprocessing the input image; extracting features from the preprocessed input image, the extracting including predicting a color label corresponding to a dominant perceptual color detected from the preprocessed input image a dominant subject from the preprocessed input image, detecting low-level image features from the preprocessed input image, and extracting mood feature information based on a description information included in the input image; classifying the extracted features into a plurality of mood/sentiments classes, using an artificial neural network; and predicting at least one of a mood or a sentiment that is present in the input image based on the dominant perceptual color and the plurality of mood/sentiments classes.

An object detection method and apparatus are disclosed. The object detection method may include acquiring identification information of an object detected from each of N (N being a preset integer of 3 or more) images continuous in order of capture from the output of a classification layer of an object detection deep learning network and correcting, based on the identification information of the object detected from each of at least two images that have been captured early in order of time, among the N images, the identification information of the object detected from an image that has been captured later in order of time than the at least two images that have been captured early in order of time, among the N images.

A method and an apparatus for processing a screen by using a device are provided. The method includes obtaining, at the second device, a display screen displayed on the first device and information related to the display screen according to a screen display request regarding the first device, determining, at the second device, an additional screen based on the display screen on the first device and the information related to the display screen, and displaying the additional screen near the display screen on the first device.

A system and method for reducing the responsibility of the user significantly by applying an optical system that can identify container like sample tubes with respect to their characteristics, e.g., shapes and inner dimensions, from their visual properties by capturing images from a rack comprising container and processing said images for reliably identifying a container tyle.

An image processing apparatus includes at least one processor. The processor is configured to execute calcification image detection processing of detecting a calcification image based on a plurality of tomographic images obtained from a series of a plurality of projection images obtained by tomosynthesis imaging of a breast, region-of-interest image group generation processing of generating a region-of-interest image group by cutting out, as a region-of-interest image, a region including the calcification image detected by the calcification image detection processing from each of the plurality of projection images, variance value calculation processing of calculating a variance value of feature amounts of each of the region-of-interest images included in the region-of-interest image group, and shape type determination processing of determining a type of a shape of the calcification image based on the variance value calculated by the variance value calculation processing.

The present disclosure relates to systems, devices, and methods to augment a two-dimensional image.

A work machine includes: a vehicle body front part to which a front wheel is attached; a vehicle body rear part which is coupled to the vehicle body front part through an articulated mechanism and to which a rear wheel is attached; a working equipment coupled to the vehicle body front part; a headlight supported by the vehicle body front part and arranged above the front wheel; and a three-dimensional measurement device arranged on an outer side of the headlight in a vehicle width direction that is in parallel with a rotation axis of the front wheel.

A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.