An image recognition method based on a three-way decision and a CNN

Abstract

The invention discloses an image recognition method based on a three-way decision and a CNN. The method comprises the following steps of inputting a sample data set image to train a CNN classifier; introducing three decision-making ideas in an image segmentation stage, and obtaining three decision-making classifiers by utilizing a positive data set image and a negative data set image which are obtained by classification of a CNN classifier; dividing the image into a positive region, a negative region and a delay decision region by using three decision classifiers; performing iterative classification processing on the delay decision area divided by the classifier; judging whether the remaining delay decision area reaches a critical value or not; when the delay decision area reaches a critical value, indicating that the to-be-identified image cannot be segmented again, and then performing CNN image identification on all positive areas. According to the present invention, the CNN image recognition technology and the three decision theories are combined, the useful information in the image can be fully utilized, and the higher recognition rate is achieved.

Description

technical field [0001] The invention relates to the technical fields of intelligent information processing and high-performance image recognition, in particular to an image recognition method based on three-way decision-making and CNN. Background technique [0002] Image recognition is a technology that uses computers to process, analyze and understand images to identify different targets and objects. Existing image recognition methods are too busy to study the underlying semantics of the image. Due to the performance of the computer itself, it can only execute a single operation instruction programmatically, resulting in a low recognition rate of the image in general methods. Therefore, an image recognition technology based on three-way decision (Three-way Decision, 3WD for short), convolutional neural network (Convolutional Neural Network, CNN) and other methods has been proposed. [0003] Among them, three-way decision-making is a method developed in recent years to deal...

AI Technical Summary

Problems solved by technology

However, the processing process of convolutional neural network recognition is single, not flexible enough, and the required eigenvalues ​​are more specific, resulting in very fixed features; in addition, the convolution process easily leads to the loss of some useful information in the image, making the recognition accuracy of the image lower. too ideal

Images