基于多层次模糊增强的自适应Canny边缘检测算法  

AN ADAPTIVE CANNY EDGE DETECTION ALGORITHM BASED ON MULTILEVEL FUZZY ENHANCEMENT

作　　者：崔桐[1] 韩峰[1] 张双娟[1] 

机构地区：[1]内蒙古工业大学机械学院,呼和浩特010062

出　　处：《内蒙古工业大学学报（自然科学版）》2006年第1期71-75,共5页Journal of Inner Mongolia University of Technology：Natural Science Edition

基　　金：内蒙古自治区自然科学基金项目(NO.200308020219)

摘　　要：边缘检测技术是图像预处理中最重要的技术之一.在对C anny的最佳边缘检测算子进行理论及实验研究的基础上,利用广义模糊集(GFS)理论,给出了基于多层次模糊增强图像区域对比度的广义模糊算子来取代传统的高斯算子,从而增强了图像的层次结构,并实现了图像边缘的自动提取.试验表明,改进算法具有较高的信噪比,能达到比较理想的边缘检测效果.In image preprocessing,edge detection improvement leaves much to be desired. This paper,on the basis of theoretical and experimental study of Canny＇s optimal edge detection operator, introduces a novel Canny edge detection scheme,in which the conventional Gauss operator is replaced by a general fuzzy operator （GFO） featuring multilevel fuzzy enhancement of contrast. It is proven that this scheme can enhance image hierarchy and make the image edge detection automatic. Experiments have shown that the improved algorithm can improve SNR and furnish much better edge detection results.

关 键 词：边缘检测 CANNY算法 模糊增强 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]