基于方向信息测度的最小模糊度准则边缘检测  

Edge Detection Based on the Direction Information Measure and Minimum Measures of Fuzziness Principle

作　　者：李懿[1] 张运杰[1] 王威娜[1] 张晓娜[1] 

机构地区：[1]大连海事大学数学系

出　　处：《模糊系统与数学》2007年第3期143-151,共9页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(60573072);辽宁省教育厅高校科研项目(2005073)

摘　　要：将像素点的方向信息测度作为判别边缘点的特性指标,借用Huang等构造的自适应确定分割阈值的思想,本文提出了一种基于方向信息测度的最小模糊度准则边缘检测方法。文中提出的方法,一方面由于采用了方向信息测度,可以很好地将边缘点和非边缘点区分开来;另一方面通过最小化模糊度,自适应地将给定图像的所有像素点按照方向信息测度分成两类,从而达到提取边缘的目的。实验结果证明,我们提出的方法能够很好地判别边缘点,有效地提取图像的边缘。In this paper, we use the direction information measure of pixels of input image as the edge characteristic index, and then combine with the basic thought of Huang that selects the threshold of image automatically. A new detecting edge method is presented based on the minimum the measures of fuzziness principle and the direction information. Thus, on the one hand, we can distinguish the pixels of input image into edge and nonedge effectively due to applying direction information measures; on the other hand, according to the direction information measures, we can divide the pixels into two types through minimizing the measures of fuzziness automatically such that we obtain the edge of image. The experimental results indicate that the proposed method has demonstrated good performance in distinguishing and extracting boundaries.

关 键 词：模糊度 方向信息测度 边缘检测 阈值 

分 类 号：O159[理学—数学]