用前向网实现噪声图象的边缘提取  

Detecting Noisy Images Edge by Feedforward Neural Network

作　　者：王磊[1] 莫玉龙[1] 戚飞虎[1] 

机构地区：[1]上海交通大学,上海大学

出　　处：《上海大学学报（自然科学版）》1996年第5期549-555,共7页Journal of Shanghai University:Natural Science Edition

摘　　要：本文提出采用多层前向网及改进的ＢＰ算法，对经Ｃａｎｎｙ最佳边缘检测算子处理噪声图象后得到的高、低门限图进行不连续轮廓的并行“修补”，能够较快地得到信噪比高的边缘图象．This paper describes a method to detect noise-blurred image's edge by feedforward neural network with modified BP algorithm. Owing to neural network's parallel characteristic, non-continuous contour may be marked by low-thresholded image and high-thresholded image, both of which were obtained from Canny' s optimal edge operator, more quickly and precisely.

关 键 词：边缘提取 BP算法 前向网 图像信号处理 噪声 

分 类 号：TN941.1[电子电信—信号与信息处理]