关键词: 图像分割, 脉冲耦合神经网络, 最大相关准则

Abstract: Pulse Coupled Neural Network（PCNN） is a new generation which has a biological background of artificial neural network，reflects excellent performance in the image segmentation.But the problems of PCNN model parameter estimation and threshold iteration are not been resolved.This paper combines one dimension maximal correlative criterion and two dimension maximal correlative criterion to estimate the neuron parameters，achieves the automation of image segmentation and reduces the complexity of computing.Simulation results show that the proposed method results in the segmentation map and computational complexity compared with the related literature have been improved，and has better usability.

Key words: image segmentation, Pulse Coupled Neural Network（PCNN）, maximal correlative criterion