A particle swarm optimization algorithm for neural networks in recognition of maize leaf diseases

Abstract

The neural networks have significance on recognition of crops disease diagnosis， but it has disadvantage of slow convergent speed and shortcoming of local optimum. In order to identify the maize leaf diseases by using machine vision more accurately, we propose an improved particle swarm optimization algorithm for neural networks. With the algorithm, the neural network property is improved. It reasonably confirms threshold and connection weight of neural network, and improves capability of solving problems in the image recognition.At last, an example of the emluatation shows that neural network model based on pso recognizes significantly better than without optimization. Model accuracy has been improved to a certain extent to meet the actual needs of maize leaf diseases recognition.