The Retinex Enhancement Algorithm for Low-light Intensity Image Based on Improved Illumination Map

Due to the low brightness of the images taken in low-light intensity conditions, the image processing precision will be affected. In this paper, the Gamma Function based on the brightness average and the weighted fusion method according to gray entropy are proposed. They are combined with the improved Retinex algorithm. Firstly, the maximum values of R, G, and B channels in the original image are extracted to form the primary illumination map. Secondly, the illumination map is optimized by the optimization problems and adjusted by using the Gamma correction function based on the average brightness value. Finally, the illumination map and detail layer are fused by a weighted fusion algorithm of gray entropy to obtain the reflection map. Reflection maps are used as enhancement results. The algorithm proposed in this paper can improve the brightness and can maintain light distribution in the original image and has less color distortion.