一种基于脉冲耦合神经网络和图像熵的自动图像分割方法

2002年1月通信学报Vol.23 No.1第23卷第1期JOURNAL OF CHINA INSTTTUTE OF COMMUNICATIONS January 2002

学术论文

一种基于脉冲耦合神经网络和图像熵的自动图像分割方法

马义德1,2戴若兰1李廉2

?ê?à兰州 730000?ê?à兰州 730000

90年代发展形成的脉冲耦合神经网络模型特别适合于图像分割

但众所周知

而且同时还取决于循环迭代次数的确定选择准则

正因如此选择合适的准则来确定N是PCNN图像分割的关键

本文结合图像统计特性和PCNN参数模型提出了熵值最大准则对于PCNN的理论研究和实际应用具有非常重要的现实意义

脉冲耦合神经网络熵

O 236 文献标识码1000-436X01-0046-06

Automated image segmentation using pulse coupled

neural networks and image’s entropy

MA Yi-de1,2, DAI Ruo-lan1 , LI Lian2

(1. The State Key Laboratory of Arid Agroecology, Lanzhou University, Lanzhou 730000, China;

2. School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, China)

Abstract: Pulse-coupled neural network(PCNN) based on Eckhorn’s model of the cat visual cortex find many applications in image processing, including segmentation, edge extraction et al. As all known, the performance of the image segmentation depends not only directly on the adjustment of PCNN parameters and the statistical properties of image but also on the cyclic iteration times N of PCNN. If the parameters have been properly set, it turns out to be essential to select a suitable criterion to determine N. While N is usually determined by means of visual judgement which decreases the efficient

收稿日期： 2001-03-02

39770375甘肃省自然科学基金资助项目

作者简介：马义德(1963–)?ê?àáù??è?2?ê?

DSP与信号实时编码技术女兰州大学高级工程师

GISà?á?(1948–)é?????1èè?2?ê?éúμ?ê|êy×?í???′|àí??ê?μè

万方数据