Contrast enhancement of images using human contrast sensitivity

Study of contrast sensitivity of the human eye shows that our contrast discrimination sensitivity follows the weber law for suprathreshold levels. In this paper, we apply this fact effectively to design a contrast enhancement method for images that improves the local image contrast by controlling the local image gradient. Unlike previous methods, we achieve this without segmenting the image either in the spatial (multiscale) or frequency (multi-resolution) domain. We pose contrast enhancement as an optimization problem that maximizes the average local contrast of an image. The optimization formulation includes a perceptual constraint derived directly from human suprathreshold contrast sensitivity function. Then, we propose a greedy heuristic, controlled by a single parameter, to approximate this optimization problem. The results generated by our method is superior to existing techniques showing none of the common artifacts of contrast enhancements like halos, hue shift, and intensity...

• Type: Conference
• Year: 2006
• Where: APGV
• Authors: Aditi Majumder, Sandy Irani
• Keywords: APGV 2006, Contrast Discrimination Sensitivity, Contrast Enhancements, Contrast Sensitivity