DESIGN FOR ROBUSTNESS CONTOUR DETECTION CNN

摘要：

The cellular neural nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. This paper sets up a theorem to design robustness template CNN for contour detection in images, which provides parameter inequalities for determining parameter intervals for implementing the corresponding tasks.The contour CNN has successfully detected edges in three gray-scale images.

关键词： Cellular neural network Contour detection Gray-scale images Template design

作者: GUO-DONG LI ZHEN-YU ZHAO DE-GANG CHEN ZHEN-JUN YE

作者单位: School of Mathematics and Physics, North China Electric Power University, Beijing 102206, China School of Business and Manages, North China Electric Power University, Beijing 102206, China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 3721-3724

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）