基于视觉特性的Kirsch边缘检测算法  

An edge detection algorithm based on eyes from Kirsch operator

作　　者：于蕾[1] 陈辉[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《信息技术》2012年第5期117-120,共4页Information Technology

摘　　要：边缘是图像中最重要的信息之一,能够以较少数据量表达大量的图像信息。Kirsch算子有较好的检测效果及抗噪能力,但得到的边缘较粗,且阈值是一个不变值,自适应性差。针对以上问题,基于视觉特性理论提出了一种生成自适应阈值的方法,对已有的一种边缘细化算法提出了改进,获得了较好的效果。Edge image is one of the most important information, which make it possible to express enormous information with less data quantity of images. Kirseh operator has good effect, good antinoise ability while edge detection. But the edge of image got is not thinner enough, and the threshold value is a changeless value, so its adaptability is a little poorer. Due to the problems above, according to the average of gray of target points around the neighborhood, combined with the human eye＇ s sensitivity to different gray, based on the experimental data, this paper proposes a method of generating adaptive threshold, and propose an improved algorithm to get the edge of to thick. And through this method the good results were obtained.

关 键 词：边缘检测 KIRSCH算子 阈值 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]