Improved genetic neural network for image segmentation

Abstract

The paper provides the method of the improved genetic neural network for image segmentation. The method uses improved genetic algorithm BP neural network weights and thresholds to optimize, and use the definition of bipolar fitness function mapping compression to speed up neural network training speed, and then use iterative improved neural network algorithm to achieve image segmentation. The results of experimental show that the improved genetic neural network can better achieve the image segmentation, compared with the traditional method; Compared with BP neural network training speed is greatly improved.