Image recoloring for Red-Green dichromats with compensation range-based naturalness preservation and refined dichromacy gamut

People with color vision deficiency (CVD) have difficulty discriminating colors, which can cause loss of chromatic contrast in the perception affected individuals. To compensate for loss, image recoloring approaches been proposed existing studies. In state-of-the-art studies, models were built based on an approximated gamut CVD CIE L*a*b* (Lab) space, significantly deviates from original gamut. addition, luminance was not considered during recoloring. Moreover, methods also present problems, such as high computational costs and insufficient naturalness preservation . this paper, we propose a novel method to that enhances through adopting channel-considered optimization model while preserving by imposing hard constraints amount changes colors. obtain better compensation effect, fit new curved surface representing dichromacy Lab space more accurately. Furthermore, discrete solver is implemented solve problem efficiently. For effective assessment, qualitative, quantitative, subjective experiments conducted, metric, called preference, evaluate enhancement comprehensively.