Personalized Image Recoloring for Color Vision Deficiency Compensation

Several image recoloring methods have been proposed to compensate for the loss of contrast caused by color vision deficiency (CVD). However, these only work dichromacy (a case in which one three types cone cells loses its function completely), while majority CVD is anomalous trichromacy (another partially function). In this paper, a novel degree-adaptable algorithm presented, recolors images minimizing an objective constrained enhancement and naturalness preservation. To assess effectiveness method, quantitative evaluation using common metrics subjective studies involving 14 volunteers with varying degrees are conducted. The results experiment show that personalized method outperforms state-of-the-art methods, achieving desirable adapted different preserving as much possible.