A new enhancement algorithm for the low illumination image based on fog-degraded model

Abstract

A novel enhancement algorithm is presented to solve the problem of over exposure in bright areas of Low illumination image enhancement algorithm. In this paper, a model is proposed which can make the bright region gain compressed, and a complementary map can be generated which contains the bright region information. And a segmentation method is proposed to detect the bright region of the low illumination image. Meanwhile, in order to avoid colour distortion, a brightness transfer fusion strategy is used to the bright area of low illumination images. Experiments have shown that the new algorithm has higher average gradient, higher information entropy and close structural similarity to the original algorithm. So it can get better performance in dealing with the bright region of low illumination images both in subjective and objective.