An image classification method, training method, classification prediction method and related devices

Abstract

The present application discloses an image classification method, which includes: preprocessing the standard TWSVM algorithm to obtain the preprocessing TWSVM algorithm; performing binary decision tree construction operations according to the acquired training data set, and obtaining the binary decision tree according to the preprocessing TWSVM algorithm and construction. The non-leaf nodes in the fork decision tree are trained and processed to obtain the decision function of each non-leaf node; the classification and prediction processing is performed on the samples to be tested through the binary decision tree and the decision function to obtain the classification results. Expand the TWSVM algorithm based on the binary decision tree, improve the efficiency of the TWSVM algorithm in dealing with multi-classification problems, and improve the accuracy of nonlinear problems through the binary decision tree constructed by kernel clustering. This application also discloses a The image classification training method, classification prediction method, image classification system, image classification device, and computer-readable storage medium have the above beneficial effects.

Description

Technical field [0001] The present application relates to the field of machine learning technology, in particular to an image classification method, a training method, a classification prediction method, an image classification system, an image classification device, and a computer-readable storage medium. Background [0002] With the development of technology, the degree of computer intelligence is getting higher and higher. Among them, computer vision is a major direction of computer intelligence research. A core problem in computer vision is the classification of images. Specifically, image classification is an abstract description of the input picture, determining whether the image data is a class in a given classification. Image classification has many application scenarios in actual operation, and other computer vision problems, such as object positioning, image segmentation, etc., are based on image classification. Moreover, in the information age, it is unrealistic to lab...

AI Technical Summary

Problems solved by technology

However, due to the relatively simple method used to calculate the maximum distance between classes, the optimal decision tree may not be obtained when facing some problems, especially when dealing with some nonlinear problems.

Images