Scotopic Vision Image Enhancement Algorithm Based on Retinex Model

Abstract

Scotopic vision image enhancement has problems of over-enhancement and halo artifacts, based on retinex theory, this article proposes illumination map estimate method to enhancement image to solve those problems. Specifically, we extracted the image of Max-RGB and Y channel as global and local initial illumination map respectively. Then, we improved weighted guided filter to reduce halo artifacts. Next, we refined the initial illumination maps with weighted average, improved weighted guided filtering and gamma correction, as the final illumination map. Finally, the enhanced result is obtained by the corrected illumination map according to retinex theory. Experiments shown that the method can obtain results with less lightness distortion and reduce halo artifacts compared with that of several state-of-the-art methods.