PCNN和最大相关准则相结合的图像分割方法  

Image segmentation algorithm combined PCNN with maximalcorrelative criterion

作　　者：邓成锦[1] 聂仁灿[1] 周冬明[1] 赵东风[1] 

机构地区：[1]云南大学信息学院通信工程系,昆明650091

出　　处：《计算机工程与应用》2011年第14期177-179,共3页Computer Engineering and Applications

基　　金：国家自然科学基金 No.6106500;云南省自然科学基金(No.2005F0010M);云南大学重点项目(No.2004Z007C);云南大学青年项目(No.2007Q024C)~~

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。Pulse Coupled Neural Network（PCNN） is a new generation which has a biological background of artificial neu- ral 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 di- mension 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

关 键 词：图像分割 脉冲耦合神经网络 最大相关准则 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]