基于Gabor滤波器的图像边缘检测算法  

Edge detection algorithm based on odd Gabor filter

作　　者：高晓兴[1] 曹丽[2] 常桂然[2] 

机构地区：[1]东北大学软件学院,沈阳110004 [2]东北大学信息科学与工程学院,沈阳110004

出　　处：《计算机应用》2008年第10期2625-2627,共3页journal of Computer Applications

基　　金：教育部博士点基金资助项目(20030145017);沈阳市科学技术计划项目(1071121-2-00)

摘　　要：采用Canny算子进行边缘检测时,需人工设定高低2个阈值。对不同的图像采用相同的阈值,边缘检测效果差异很大,这一点限制了Canny算子在实际中的应用。针对这一问题,提出了一种基于Gabor奇部滤波器的边缘检测方法,在不同的尺度下分别采用非极大值抑制,然后利用Canny算子在高低阈值图像中查找边缘点的方法对图像进行边缘检测,无需人为地设定任何参数。实验结果表明这种算法不但克服了Canny算法中人为设定阈值的缺陷,而且能有效去除图像中的伪边缘。Using Canny edge detection operator, two thresholds need to be set by users. Results of edge detection vary widely when using the same threshold on different images. This limits the practical application of Canny operator. To solve this problem, an edge detection was presented using odd Gabor filter. In this method, non-maximum inhibition was done, and then high and low thresholds were used to detect the edges of images. The experimental results show this algorithm can not only overcome the defects of Canny algorithm, but also effectively wipe off the pseudo-edges of images.

关 键 词：边缘检测 Gabor奇部滤波器 CANNY算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]