This invention makes it possible to build an image identification model having high accuracy of identification using divided training images into which training images are divided. An image identification system includes: an image dividing unit which divides training images of a first training data set and assigns a label assigned to a training image from which dividing occurs to the divided training images as tentative labels; a texture index computing unit which computes texture indexes for each of the divided training images; a tentative label prediction model building unit which builds a tentative label prediction model to predict tentative labels assigned to the divided training images based on the texture indexes; and a label comparison unit which compares first tentative labels assigned to the divided training images with second tentative labels predicted with respect to the divided training images by the tentative label prediction model and extracts divided training images for which there is discrepancy between the first and second tentative labels as those images for which it is highly necessary to modify tentative labels.

This invention makes it possible to build an image identification model having high accuracy of identification using divided training images into which training images are divided. An image identification system includes: an image dividing unit which divides training images of a first training data set and assigns a label assigned to a training image from which dividing occurs to the divided training images as tentative labels; a texture index computing unit which computes texture indexes for each of the divided training images; a tentative label prediction model building unit which builds a tentative label prediction model to predict tentative labels assigned to the divided training images based on the texture indexes; and a label comparison unit which compares first tentative labels assigned to the divided training images with second tentative labels predicted with respect to the divided training images by the tentative label prediction model and extracts divided training images for which there is discrepancy between the first and second tentative labels as those images for which it is highly necessary to modify tentative labels.

Disclosed is an electronic apparatus comprising, a memory configured to store instructions; and at least one processor connected to the memory, and configured to detect at least one object of a first-class object or a second-class object included in a target image by the electronic apparatus using an artificial intelligent algorithm to apply the target image to a learned neural network model, and identify and apply an image-quality processing method to be individually applied to at least one detected object, the neural network model is set to detect an object included in an image, as trained based on learning data such as an image, a class to which the image belongs, information about the first-class object included in the image, and information about the second-class object included in the image.

A method of remote facilities monitoring for the detection of contamination, leaks or failures in petrochemical and related facilities. Remote cameras are used to capture images of equipment to be inspected, which are transmitted to a central server. A software component on the central server applies artificial intelligence and image processing methods to detect the presence of anomalies in the images for display to an operator and potential subsequent dispatch of in person follow-up. Parallel data streams from sensors at the remote sites can be used by the software on the server to enhance the level of confidence in anomaly detection. The rl server software uses an adaptive object-detection function to analyze image data and learns over time to provide enhanced detection of interest regions and failure conditions.

An end-to-end multimodal gait recognition method based on deep learning includes: first extracting gait appearance features (color, texture and the like) through RGB video frames, and obtaining a mask by semantic segmentation of the RGB video frames; then extracting gait mask features (contour and the like) through the mask; and finally performing fusion and recognition on the two kinds of features. The method is configured for extracting gait appearance feature and mask feature by improving GaitSet, improving semantic segmentation speed on the premise of ensuring accuracy through simplified FCN, and fusing the gait appearance feature and the mask feature to obtain a more complete information representation.

An end-to-end multimodal gait recognition method based on deep learning includes: first extracting gait appearance features (color, texture and the like) through RGB video frames, and obtaining a mask by semantic segmentation of the RGB video frames; then extracting gait mask features (contour and the like) through the mask; and finally performing fusion and recognition on the two kinds of features. The method is configured for extracting gait appearance feature and mask feature by improving GaitSet, improving semantic segmentation speed on the premise of ensuring accuracy through simplified FCN, and fusing the gait appearance feature and the mask feature to obtain a more complete information representation.

The disclosure provides methods and systems for automatically generating an animatable object, such as a 3D model. In particular, the present technology provides fast, easy, and automatic animatable solutions based on unique facial characteristics of user input. Various embodiments of the present technology include receiving user input, such as a two-dimensional image or three-dimensional scan of a user's face, and automatically detecting one or more features. The methods and systems may further include deforming a template geometry and a template control structure based on the one or more detected features to automatically generate a custom geometry and custom control structure, respectively. A texture of the received user input may also be transferred to the custom geometry. The animatable object therefore includes the custom geometry, the transferred texture, and the custom control structure, which follow a morphology of the face.

Disclosed is a diagnostic apparatus for a chronic obstructive pulmonary disease (COPD) based on prior knowledge CT subregion radiomics, belonging to the field of medical imaging. The diagnostic apparatus comprises: a subregion partitioning module based on prior knowledge configured for partitioning a CT lung image of a patient into three subregions based on the CT values of the interior of the lung, wherein the CT value of the interior of the lung of a subregion 1 is in the range of (−1024, −950), the CT value of the interior of the lung of a subregion 2 is in the range of (−190, 110), and the CT value of the interior of the lung of a subregion 3 is in the range of (−950, −190); a feature extraction module configured for extracting the radiomics features of the three subregions, respectively, and obtaining the LAA-950I features.

A model generation system generates three-dimensional (3D) models for objects based on two-dimensional (2D) images of the objects. The model generation system may receive object images and generate a 3D object model for the object based on the object image. The model generation system may generate an object skeleton for the object based on the object image. The model generation system may use the object skeleton to generate pixel partitions representing parallel cross sections of the object. The model generation system may apply a machine-learning model (e.g., a neural network) to the object image to determine parameters for a shape that would best represent each parallel cross section and then generate the 3D object model for the object based on the shapes of each cross section, the object image, and the object skeleton.

A method for identifying a log of origin of a first board, comprising an identification step, during which a second board (12) is identified which was obtained from the same log (2) as the first board (11) was obtained from, a studying step, during which identifying features of the second board (12) are identified, and a recognition step during which the log (2) of origin of the first board (11) is recognised, among a plurality of known logs (2) about which saved information is available, and this is done by identifying the log of origin of the second board (12), using the identifying features of the second board (12) itself.