基于Sobel的多方向算子模板边缘检测算法  

Sobel-based edge detection algorithm for multi-direction template

作　　者：沈德海[1] 侯建[1] 鄂旭[1] 张龙昌[1] 

机构地区：[1]渤海大学信息科学与技术学院,辽宁锦州121013

出　　处：《现代电子技术》2015年第4期91-93,97,共4页Modern Electronics Technique

基　　金：国家自然科学基金:基于博弈论的高效稳定聚类算法研究(61473045);辽宁省高等学校实验室项目(L2012397);博士后基金项目(2012M520158);辽宁省"百千万人才工程"资助项目(2012921058);教育厅科研一般项目(L2012400)

摘　　要：针对传统Sobel算子存在的边缘检测方向性不强及提取边缘较粗等问题,提出了一种改进的多方向算子模板的边缘检测算法。算法增加了22.5°,45°,67.5°,112.5°,135°和157.5°六个方向算子模板,能够较好地检测出图像不同的方向边缘。模板权值根据中心像素点到邻域像素的距离及方向夹角的大小进行设定,充分考虑到了邻域内像素对中心点方向梯度的贡献大小;算法对梯度图像采用了改进的非极大值抑制方法进行细化,得到了较细的图像边缘。实验结果表明,与传统Sobel算法相比,该算法提取的边缘图像具有边缘方向性强且边缘较细的优点,具有较高的应用价值。Since the traditional Sobel operator exists the weak edge detection directivity and the extracted edge is coarse,an improved edge detection algorithm of multi-direction operator template is proposed. In the algorithm,six direction templatesare added at 22.5°,45°,67.5°,112.5°,135° and 157.5° to detect different direction edges. The templates weights are deter-mined according to the distances from center pixel to neighborhood pixels and their direction included angles,which fully considerthe contribution of neighborhood pixels to the central point direction gradient. The improved non-maximum suppression methodis used in the algorithm to refine the gradient image for getting the thinner edges. The results show that the improved algorithmhas advantages of stronger edge directivity and thinner edges in comparison with traditional Sobel algorithm. It has a high appli-cation value.

关 键 词：边缘检测 多方向算子模板 非极大值抑制 梯度图像细化 

分 类 号：TN919-34[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]