Image classification method, device and computer-readable storage medium

Abstract

The present application relates to a picture classification method, device, computer-readable storage medium and computer equipment. By obtaining each picture to be classified, input each said picture to be classified into a feature extraction model to obtain the feature vector of each picture to be classified, and obtain each According to the distribution of the feature vectors of the pictures to be classified in the feature space, the feature space is divided into categories by a finite field according to the distribution, and a picture classification result is obtained. By extracting the feature vectors of the pictures to be classified, the distribution of the feature vectors of each picture to be classified in the feature space is obtained, and the finite field division of the category is performed based on the distribution of the feature space, and the non-target pictures are removed from the target pictures to reduce non-target pictures. The impact of target pictures on the classification accuracy of target pictures solves the problem that all pictures that need to participate in classification are composed of N different target pictures and non-target pictures, resulting in low accuracy and precision of picture classification.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to a picture classification method, device, computer-readable storage medium and computer equipment. Background technique [0002] With the continuous development of Internet technology, AI artificial intelligence is being widely used in various fields. As one of the important applications of artificial intelligence, computer vision is of great help when it is necessary to classify a large number of pictures. [0003] At present, the general way to classify a large number of pictures is: to extract the corresponding feature vectors from the pictures that need to be classified, based on the common characteristics of each feature vector, divide the quantity of pictures into their respective categories according to some pre-set standards. In the class, the divided classes show different degrees of characteristics between the classes. Since all pictures that need to be c...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide an image classification method, device, and computer-readable method for image classification due to the fact that all images that need to be classified are composed of N different target images and non-target images, resulting in low accuracy and precision of image classification. Storage media and computer equipment

Images