A handwritten picture classification method based on a quantum neural network

Abstract

The invention discloses a handwritten picture classification method based on a quantum neural network. The implementation steps are as follows: (1) extracting handwritten picture features; (2) constructing a particle population of a binary quantum particle swarm algorithm; (3) constructing a convolutional neural network by using the particle population; (4) training the convolutional neural network; (5) selecting an optimal convolutional neural network; (6) judging whether the classification accuracy of the optimal convolutional neural network is smaller than 0.85 or not, and if yes, executingthe step (7); otherwise, executing the step (8); (7) updating the structure and parameters of the convolutional neural network corresponding to the position information of each particle by using a quantum updating strategy, and executing the step (3); and (8) outputting a classification result of the optimal convolutional neural network. The method has the advantages of being high in classification accuracy and capable of processing large-scale complex handwritten picture classification, and the problem that in the prior art, a large number of professional knowledge and design experiences ofthe convolutional neural network are needed is effectively solved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a quantum neural network-based handwritten picture classification method in the technical field of image classification. The present invention utilizes the uncertain characteristics of the particle swarm optimization algorithm of binary coded quantum behavior, and can automatically generate different deep neural network models for different handwritten picture data sets, which are used to extract the features of handwritten pictures and use the features for automatic classification . The invention can be applied to deal with large-scale and complex handwriting picture classification. Background technique [0002] Handwritten image classification refers to the process of converting handwritten images into Arabic numerals. It is actually a mapping process from the coordinate sequence of handwritten trajectories to Arabic numerals. It is one of the most natural and c...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it requires a lot of professional knowledge and design experience of convolutional neural networks, so it is difficult to guarantee the reliability and stability of the classification results when dealing with large-scale and complex handwritten image classification, and a large number of samples are required for training. In order to get better recognition results

However, the disadvantage of this method is that most of the convolutional neural network structures searched in the continuous search space are invalid, and it takes a lot of time to search repeatedly, which affects the efficiency of handwritten image classification

Secondly, this method always requires professional knowledge and design experience of convolutional neural network in the encoding process, and it is difficult to automatically process large-scale and complex handwritten image classification

Images