A Research of Image Difference Algorithm Based on the Correlation of Color Attributes

The CIE color difference formula was developed using simple color patches in controlled viewing conditions. They are not suitable for predicting color differences of spatially complex images. In order to quantify color differences between the original and reproduced images, we present an image difference algorithm based on image contents. This formula uses the Contrast Sensitivity Functions (CSF) to reduce the spatial complexity. The CSF serves to remove information that is imperceptible to the human visual system. This algorithm determines the color attribute weights by means of the correlation analysis between image pairs. Psychophysical experiments confirmed that the metric correlates strongly with the human perception. The proposed algorithm can be used to assess the performance of color image compressions, color image enhancement algorithms, gamut mapping algorithms and so on.