A picture processing method is provided for a computer device. The method includes obtaining a to-be-processed picture; extracting a text feature in the to-be-processed picture using a machine learning model; and determining text box proposals at any angles in the to-be-processed picture according to the text feature. Corresponding subtasks are performed by using processing units corresponding to substructures in the machine learning model, and at least part of the processing units comprise a field-programmable gate array (FPGA) unit. The method also includes performing rotation region of interest (RROI) pooling processing on each text box proposal, and projecting the text box proposal onto a feature graph of a fixed size, to obtain a text box feature graph corresponding to the text box proposal; and recognizing text in the text box feature graph, to obtain a text recognition result.

A picture processing method is provided for a computer device. The method includes obtaining a to-be-processed picture; extracting a text feature in the to-be-processed picture using a machine learning model; and determining text box proposals at any angles in the to-be-processed picture according to the text feature. Corresponding subtasks are performed by using processing units corresponding to substructures in the machine learning model, and at least part of the processing units comprise a field-programmable gate array (FPGA) unit. The method also includes performing rotation region of interest (RROI) pooling processing on each text box proposal, and projecting the text box proposal onto a feature graph of a fixed size, to obtain a text box feature graph corresponding to the text box proposal; and recognizing text in the text box feature graph, to obtain a text recognition result.

In an example, a method for adapting a machine learning model includes receiving a digital representation of a three-dimensional (3D) object; learning, using a surrogate model, relationships between a plurality of points on a surface of the 3D object; and generating, using the surrogate model, one or more predictions about fluid properties along the surface of the 3D object.

In an example, a method for adapting a machine learning model includes receiving a digital representation of a three-dimensional (3D) object; learning, using a surrogate model, relationships between a plurality of points on a surface of the 3D object; and generating, using the surrogate model, one or more predictions about fluid properties along the surface of the 3D object.

Feature descriptor matching is reformulated into a graph-matching problem. Keypoints from a query image and a reference image are initially matched and filtered based on the match. For a given keypoint, a feature graph is constructed based on neighboring keypoints surrounding the given keypoint. The feature graph is compared to a corresponding feature graph of a reference image for the matched keypoint. Relocalization data is obtained based on the comparison.

This application provides an image recognition method and apparatus, an electronic device, and a computer-readable storage medium, and relates to the field of artificial intelligence technologies. The method includes obtaining feature information corresponding to a target object in an image to be recognized, the feature information comprising blur degree information, local feature information, and global feature information; determining a category of the target object based on the feature information, and determining a confidence level corresponding to the target object; and obtaining target information corresponding to the image to be recognized according to the category of the target object and the confidence level.

This application provides an image recognition method and apparatus, an electronic device, and a computer-readable storage medium, and relates to the field of artificial intelligence technologies. The method includes obtaining feature information corresponding to a target object in an image to be recognized, the feature information comprising blur degree information, local feature information, and global feature information; determining a category of the target object based on the feature information, and determining a confidence level corresponding to the target object; and obtaining target information corresponding to the image to be recognized according to the category of the target object and the confidence level.

Techniques for adversarial attack avoidance for machine learning (ML) are disclosed. These techniques include receiving one or more images at a trained ML model and receiving attack data at the ML model. The techniques further include predicting an object depicted in the one or more images using the ML model, based on the one or more images, metadata relating to the one or more images, and the attack data. The ML model uses the metadata to prevent the attack data from changing a result of the predicting.

Systems and methods are disclosed for deep learning and classifying images of objects by receiving images of objects for training or classification of the objects; producing fine-grained labels of the objects; providing object images to a multi-class convolutional neural network (CNN) having a softmax layer and a final fully connected layer to explicitly model bipartite-graph labels (BGLs); and optimizing the CNN with global back-propagation.

An apparatus for automatic detection of the face in a given image and localization of the eye region which is a target for recognizing iris is provided. The apparatus includes an image capturing unit collecting an image of a user; and a control unit extracting a characteristic vector from the image of the user, fitting an extracted vector into a Pseudo 2D Hidden Markov Model (HMM), and an operating method thereof for detecting a face and facial features of the user.