一种改进的边缘检测算法  

An improved edge detection

作　　者：崔建军[1] 詹世富[2] 郑雄伟[2] 顾俊凯[1] 

机构地区：[1]长安大学地质工程与测绘学院,西安710054 [2]中国国土资源航空物探遥感中心,北京100083

出　　处：《测绘科学》2009年第4期55-56,共2页Science of Surveying and Mapping

基　　金：国家自然科学基金资助项目(40672173)

摘　　要：对传统的微分边缘检测算法进行了分析和评价。针对微分边缘检测算法的缺陷,提出了一种改进的边缘检测算法。新算法将待检测像素的邻域也作为一个考虑的对象,通过计算该邻域的性质,从而增加了梯度运算的可靠性。实验表明,新算法能够检测到更细的边缘,并且在椒盐噪声的情况下要优于常用的微分边缘检测算法。The capability of conventional gradient edge detection was analyzed and evaluated in this paper. In order to avoid the defects of gradient operators, we proposed new edge detection here. The new algorithm considered the neighborhood of one image pixel and improved the stability of the gradient results by introducing the value of the neighborhood to the gradient. The edge detection results of test image show that the new method can detect thinner edges and more reliable under salt ＆ pepper noisy condition.

关 键 词：边缘检测 LOG SOBEL 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]