图象边缘检测的环形统计算法

Loop-Statistical Approach for Edge Detection

利用假设检验的统计理论,使平滑噪声和检测边缘同时进行是边缘检测的一种有效方法。本文描述了一种新的统计法——环形统计算法。该算法是根据阶跃边缘加白噪声模型建立起来的。文中给出了严密的理论推导和算法的实现步骤。为了与同类方法比较,文中还给出了一种性能测度方法。利用该方法,我们将环形算法与sobel 算法进行了比较。对于理论图象及实际噪声图象的检测结果表明,环形统计算法是在噪声图象中进行边缘检测的一种有效的方法。

The algorithm in which detecting edge and smoothing noise arecontemporized,based on the statistical theory of hypothesis testing,is an eff-ective way of edge detection.In this paper a new statistical algorithm——Lo-op-Statistical Algorithm with the model of unit function and white noise isproposed.The derivation and procedure of the algorithm are given here in det-ail.For comparing the algorithm with others.We define a new decision ruleto evaluate edge detections,by which we compare our algorithm with Sobel'salgorithm.From the experimental results of theoretic images and a real image,it isshown that the Loop-Statistical Algorithm is usefull and effective for detec-ting in a noisy image.