A color image edge detection method based on entropy operator

Abstract

On the basis of making full use of the rich color information of color images, an edge detection method based on entropy operator in 1αβ space is proposed. In the color image space of 1αβ with the least correlation, the two-threshold method based on Shiozaki entropy operator is adopted to extract the edge of color image, which can effectively detect the edge of the region with little change in brightness, chroma or the region with dark light, and obtain rich edge information.