Curve Fitting Based Sub-pixel Edge Detection Algorithm

Abstract

A novel high-accuracy image edge detection algorithm at sub-pixel level based on curve fitting of gauss function is proposed. Firstly, approximate positioning of edge detection is carried out by means of canny operator to find location of edge point at pixel level; Secondly, gauss function is employed as fitting function and least square method is employed as curve fitting method to find location of edge point at sub-pixel level. The experiment results show that the proposed algorithm can position accurate edge at sub-pixel level, and has strong robustness to the noise and shorter running time, and effectively improve the positioning precision of image edge extraction.