Image edge extraction based on weighted fusion of gray scale, color and texture using PSO

Abstract

Image edge detection is one of the most important fields in image processing that helps extracting image important information and get rid of redundant data. Many different methods have been introduced to date. Each of these methods has its own advantages and disadvantages. In this paper, a fusion method that uses different aspects of image to cover some of these issues is researched. Particle swarm optimization is used to train weights for the fusion method named weighted averaging. Point of this research is to achieve better results in comparison with previous and classic methods. The results show better accuracy comparing with synthesized methods, Canny, Sobel and other classic methods.