Canny算子中Otsu阈值分割法的运用  

Application of Otsu thresholding method on Canny operator

作　　者：李华强[1] 喻擎苍[1] 方玫[1] 

机构地区：[1]浙江理工大学信息电子学院,浙江杭州310018

出　　处：《计算机工程与设计》2008年第9期2297-2299,共3页Computer Engineering and Design

基　　金：国家自然科学基金项目(50575211)

摘　　要：Canny算子只要能适当地选择其参数就能提取物体清晰的轮廓。利用类间方差最大化阈值分割算法(Otsu)能够计算出对Canny算子性能具有决定意义的高门限值,然后将这门限值运用于Canny算子来检测物体边缘。从实验结果看,Otsu算法应用于Canny算子中门限选择,改善了Canny算子的边缘提取效果,取得了预计的成果。Canny algorithm can be used in obtaining the clear object contour by setting the appropriate parameters. The Otsu algorithm can calculate the high threshold which is significant to the Canny algorithm, and then this thresholding can be used in the Canny algorithm to detect object＇s edge. The test result shown that the Otsu algorithm solves the threshold＇s setting in Canny algorithm and improves the effect of edge-distilling of the Canny algorithm, and achieves the expect result.

关 键 词：图像分割 最大类间方差法 阈值 参数 边缘检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]