Edge detection: A statistical approach
Amiya Halder, Nilabha Chatterjee, Arindam Kar, Swastik Pal, Soumajit Pramanik · 2011
This paper describes a novel edge detection algorithm for gray scale images. The proposed method is based on the neighborhood similarity of a pixel using a pre-defined intensity range and simple statistical approach. Then using three or four neighboring boundary pixel to detect a noise and reduced this noise. Many experiments were carried out to evaluate and compare the performance of the proposed algorithm. This new detector outperforms the previously available classical edge detectors.