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

摘要： 脉冲耦合神经网络（PCNN）是有着生物学背景的新一代人工神经网络，在图像分割方面体现了优异的性能。PCNN模型在参数估计和阈值迭代方面的问题还有待解决。将一维最大相关准则和二维最大相关准则相结合来估计神经元参数，实现了图像分割的自动化并降低了运算的复杂性。仿真结果表明，该方法在分割图效果和运算复杂度方面都得到了提高，具有较好的实用性。

关键词: 图像分割, 脉冲耦合神经网络, 最大相关准则