文献类型：会议论文

英文题名：A CNN-based Edge Detection Algorithm for Remote Sensing Image

作者：Xu, Guo-bao[1,2];Zhao, Gui-yan[1];Yin, Lu[2];Yin, Yi-xin[2];Shen, Yu-li[3]

机构：[1]Guangdong Ocean Univ, Informat Sch, Zhanjiang 524088, Peoples R China;[2]Univ Sci & Technol Beijing, Sch Informat Engn, Beijing 100083, Peoples R China;[3]ZhongKai Univ Agr & Technol, Guangzhou 510225, Guangdong, Peoples R China

会议论文集：20th Chinese Control and Decision Conference

会议日期：JUL 02-04, 2008

会议地点：Yantai, PEOPLES R CHINA

语种：英文

外文关键词：Remote Sensing Image; Edge Detection; Cellular Neural Networks; Template

外文摘要：With the development and applications of satellite remote sensing technology, the edge detection accuracy of remote sensing image is increasingly high. As the gray remote sensing image has a lot of noise, even image brightness, and vague edge, a novel edge detection algorithm based on cellular neural network (CNN) is presented. in the algorithm, image filtering, gray threshold segmentation, dilation and erosion, and edge detection using CNN are performed for remote sensing image successively. The experimental results show that, compared to the traditional edge detection algorithms of Sobel operator and Canny operator, the proposed edge detection algorithm can not only effectively eliminate the influence of the noise on edge detection, but also quickly detect the complete image edge.