Statistical Analysis Based On Nonparametric The Changing Point Of Image Edge Detection Algorithms

Statistical method is one of important methods on edge detection of com-puter vision. The traditional edge detection algorithms have the defect losing details of the edge and the defect enhancing noise in the non-edge, first and foremost, this paper proposed a method of edge detecting which is based on the change point statistic analysis, then a novel method of edge detection of noisy gray scale image was proposed which is based on the nonparametric change point statistic analysis. It not only minimised the need for a priori information about images, but also didn’t filter any noise.Furthermore, we studied some problems for gray level images to which we add Gaussian white noise and salt and pepper noise in these methods.At last,to compare with well-known Sobel algorithm and Canny algorithm edge detectors in MATLAB, this approach not only detects real boundary of image, but also effectively suppresses the impact of two types of noises on edge detection. This new approach makes great progress. The main contents of all chapters is introduced as follows:In the first chapter, the background of this paper is introduced as well as some important results obtained by the previous studies.In chapter two, there are some significant edge detection algorithms and their advantages and disadvantages.In chapter three,there are some classical change point statistic analysis al-gorithms and their advantages and disadvantages.In chapter four,this chapter proposed a method of edge detecting which is based on the change point statistic analysis because it minimises the need for a priori information about images. What’s more,we studied some problems for gray level images to which we add Gaussian white noise and salt and pepper noise in this method. To compare with well-known Sobel algorithm and canny algorithm, this approach not only detects real boundary of image, but also ef-fectively suppresses the impact of two types of noises on edge detection.In chapter five,the traditional edge detection algorithms have the defect los-ing details of the edge and the defect enhancing noise in the non-edge, so a novel method of edge detection of noisy gray scale image was proposed which is based on the nonpar ametric change point statistic analysis. Experimental results show that the algorithm is superior to Sobel algorithm, and can suppress Gaussian white noise of low SNRT and salt and pepper noise of high density.In all,it is a valid method of edge detection for gray images contaminated by noise.