Image recognition method based on gradient-guided evolutionary algorithm

Abstract

The invention discloses an image recognition method of an evolutionary algorithm based on gradient guidance. The method mainly comprises the following steps: 1, acquiring image samples to construct a training sample data set; 2, a parent population is initialized, a gSBX operator is used for the parent population in the mating selection process to obtain a filial population, the parent population is added into the filial population, non-dominated sorting is conducted on the filial population, and a plurality of first individuals are selected from the sorted population to serve as an optimal individual population; 3, dominated solutions are deleted from the optimal individual population, a sparse stochastic gradient method SGD is used for conducting fine adjustment on weight variables of all the remaining individuals in the population, and an attribute set of one individual is selected in an inflection point area on the Pareto leading edge face of the population to serve as a variable of a final training model. According to the method, the image recognition model is optimized through the evolutionary algorithm, so that the accuracy of the model in image recognition can be improved, and the training cost and memory consumption of the neural network are reduced.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an image recognition method. Background technique [0002] Image recognition is a series of processing processes such as comparing and calculating the stored information with the current picture information to realize the recognition of the image. Image recognition is an important field of artificial intelligence, such as face recognition, which is a biometric technology for identification based on human facial feature information. With the advancement of technology, in image recognition, how to quickly and efficiently extract target features and establish corresponding image recognition models is an important and key issue in image recognition. [0003] The currently commonly used image recognition method is mainly Convolutional Neural Networks (CNN). Since weights play a decisive role in classification performance in a CNN, the high CNN complexity poses a seri...

AI Technical Summary

Problems solved by technology

Although most of the evolutionary methods for training large-scale neural networks aim to solve the curse of dimensionality by reducing the search space (i.e., the number of weights to optimize), this may miss the optimal search region and increase the possibility of being stuck in a local optimum , cannot achieve the best image recognition results

Images