Analysis and improvement of SUSAN algorithm

Abstract

A modified Smallest Univalue Segment Assimilating Nucleus (SUSAN) algorithm based on the local gray value character of an image is presented here. Beginning with an explanation of the principle of edge detection and noise reduction, we find SUSAN algorithm is immune to all noise points but the isolated noise points. To improve this, an original edge response formulation is optimized by imposing constraint conditions. Then a set of anti-noise tests were run to compare our scheme with the original algorithm and other popular edge detectors. The results show that for Gaussian noise and salt-and-pepper noise, the improved SUSAN algorithm performs much better than the original one in view of sensitivity to noise and detection of edges, and especially for salt-and-pepper noise the improved SUSAN algorithm works best among the all detectors tested here.