Using Color Difference Equations for Calculating Gradient Images

Abstract

Recent studies have pointed out to properties such as self-similarity, complexity, and anisotropy as some of the universal characteristics seen in aesthetic paintings. New measures for evaluating the mentioned properties in images were introduced based on the Pyramid Histogram of Gradients (PHOG) features. It is clear that an influential step in calculating PHOG features is how the gradient image is calculated. While such calculations seem straightforward for greyscale images the same could not be said for color images. In this paper, we use color difference equations to propose a new method to calculate the gradient of a color image. Such approach seems a good option to point out the color difference between two patches from a standard observer. Results show that compared to previous methods, the proposed approach gives comparable results. Keeping in mind that color difference equations are specifically proposed to evaluate color difference it seems suitable to use the proposed approach for future color image gradient calculations.