Image classification method and device, computer device and storage medium

Abstract

The invention relates to an image classification method and device, a computer device and a storage medium. The method comprises the steps of obtaining a to-be-classified image; classifying the to-be-classified image by adopting a preset classification model to obtain a category to which a plurality of different attributes of the to-be-classified image belong, wherein the image to be classified is an image subjected to geometric correction, and the classification model is a model for performing multi-task processing on to-be-classified images by adopting an attention mechanism. By adopting the method, the image classification accuracy can be improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an image classification method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of science and technology, artificial intelligence technology has been widely used in people's life and work, especially for image recognition and processing has an irreplaceable position. [0003] Taking face image recognition as an example, computer equipment can use traditional neural network models to recognize and classify face images, so that it can distinguish whether glasses are worn in face images, or whether the mouth is closed or not. [0004] However, the traditional neural network model is usually a multi-layer convolutional neural network model. Using this model to identify the attributes of face images, the recognition results are not accurate. Contents of the invention [0005] Based on this, it is necessary to prov...

AI Technical Summary

Problems solved by technology

[0004] However, the traditional neural network model is usually a multi-layer convolutional neural network model. Using this model to identify the attributes of face images, the recognition results are not accurate.

Images