Low Light Image Contrast Enhancement Based on Linear Fusion with an Optimized Weight

This paper presents an approach to low light image contrast enhancement whose objective is to improve the visual quality of an image. To this end, a linear image fusion with two images is applied in this study. The two images are the input image and its histogram equalized image. For better performance, we use a metaheuristic optimization algorithm called the whale optimization algorithm to find an optimal weight for the linear fusion, where a patch-based contrast quality index is used as a fitness function. The proposed approach is verified by hundreds of low contrast images. The result indicates that our approach has a superior performance to the comparison approaches, conventional histogram and contrast limited adaptive histogram equalization in terms of patch-based contrast quality index and subjective visual quality.