一种基于灰度差统计的边缘检测方法  

An Edge Detector Based on Gray Level Difference Analysis

作　　者：殷润民[1] 平洁[1] 柴旭东[1] 李伯虎[1] 

机构地区：[1]北京航空航天大学自动化学院,北京100083

出　　处：《计算机工程》2006年第8期201-203,共3页Computer Engineering

基　　金：国家"十五"预研专题基金资助项目(413090303)

摘　　要：提出了一种新的基于灰度差统计的边缘检测方法。该方法基于全图的灰度差统计获得初步边缘判定阈值,可以降低边缘检测结果对噪声的敏感程度,并且不需要进行边缘方向估计,而是引入灰度脊跟踪优化算法,使边缘检测结果具有连续性和准确性。由于使用了检测结果优化算法,有效地避免了一条真实边缘对应多条边缘检测结果的情况。实验证明该方法应用在大部分真实图像的边缘检测效果优异,同时运行速度能满足大部分边缘检测应用的需要。This paper proposes an edge detection algorithm based on gray level difference analysis. The processing of the novel edge detector not only is isotropic but also educes ＇gray-level ridge＇ to insure the results to be continuous and simultaneously reduces the detector＇s sensibility to noise. Optimal non-maximum condensation method is used to effectively guarantee only one response to a single edge. Experimental results prove that the proposed approach are given works well over most images, and is fast enough for real time applications.

关 键 词：图像处理 边缘枪测 模式识别 厌度差 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]