An improved Morphological Edge Detection Method for Color Images of Cotton Foreign Fibers

摘要

Most conventional color edge detectors have shortcomings such as high computational cost, difficulty in implementation and missing edges. In this paper, we propose a new, simple and effective method for edge detection in color images. Firstly, color images were captured, and then the edge of color images were detected by edge detection method which is based on improved mathematical morphology. In this edge detector, the new designed operators is fit for most color images of cotton foreign fibers. Both are used simultaneously to describe the color images including more edges than usually used. The experiment results indicate that the proposed method can segment the high-resolution color images of cotton foreign fibers directly and precisely. Fast, easy to implement and satisfactory edge detection due to its characteristics is accomplished with the new designed operators.