Multi-Exposure Image Fusion Method Based on Independent Component Analysis

Abstract

Aiming at the problems that some detailed information cannot be effectively retained and the color is distorted in MEF (multi-exposure image fusion), this paper proposes a MEF method combining with signal decomposition. In this method, the process of decomposing signals using ICA (independent component analysis) is added to the HybridHDR algorithm. The key to MEF is the fusion of the luminance channel, so different fusion methods are used for the luminance channel and the chrominance channel. Because the details under different brightness conditions are different, this paper expands the images of different brightness into a set of one-dimensional signals, and uses ICA to perform signal decomposition, so that more details are extracted and retained in the final resulting image. Then combine HybridHDR and ICA to further extract the details in the multiple-exposure image, thereby improving the quality of the fused image. Experimental results show that the proposed method can improve the overall quality of the final fusion result, and in some scenes, it has more prominent detail retention ability than other existing methods, while still maintaining the color of the original exposure image.