基于参数自适应CNN的灰度图像边缘检测  

Edge detection of gray-scale images based on self-adaptive CNN

作　　者：张莹[1] 王太勇[1] 黄国龙[1] 冷永刚[1] 

机构地区：[1]天津大学机械工程学院,天津300072

出　　处：《计算机工程与应用》2008年第18期160-162,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.50675153);天津市自然科学基金(the Natural Science Foundation of Tianjin of China under Grant No.07JCYBJC04600);国家高技术研究发展计划(863)(the National High-Tech Research and Development Plan of China under Grant No.2006AA04Z146)

摘　　要：边缘是图像的重要特征。在应用细胞神经网络提取图像边缘时,网络的稳定性和参数的选择是关键。文中推导了细胞神经网络的稳定条件,并提出了网络参数的自适应设计思路。基于Matlab7.0平台,通过编写仿真程序,检测灰度图像边缘,得到良好效果。实验证明,该法还能有效抑制噪声的干扰。Edge is an important character of the image.The stability of the network and the parameter choice are the key problems when Cellular Neural Network （CNN） is used to pick up the image edge.The stable condition of CNN is discussed,and the self-adaptive template parameters of the network are fixed reasonably.Based on Matlab 7.0,the simulation applied to the edge detection has presented its validity in the image processing,as well as the noise control.

关 键 词：边缘检测 细胞神经网络 稳定性 模板参数 自适应 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]