Low-light image enhancement based on Retinex theory for beam-splitting prism system

Abstract

The existing color image enhancement methods are utilized for the most part to directly improve the color image that is obtained through the use of a Bayer array camera, whereas the color image that is obtained through the use of a prism camera is the result of the fusion of three primary color images that have been collected independently. As a result, a method for enhancing color photographs based on three images of primary colors that have a low level of light has been proposed. In this paper, we first transfer RGB to HSV space for image enhancement. In the V channel, we use guided filtering combined with improved SSR method to better preserve edge information. Then the S channel is adjusted adaptively to make the image look more natural. Finally, the image is transferred from HSV space back to RGB space. Compared with other traditional methods, our method achieves better results in PSNR, SSIM and NIQE, and has less computational complexity.