Enhancement and Noise Suppression of Single Low-Light Grayscale Images

Low-light images have low contrast and high noise, making them not easily readable. Most existing image-enhancement methods focus on color images. In the present study, an enhancement denoising algorithm for single low-light grayscale is proposed. The based multi-exposure fusion framework. First, basis of tone-mapping operators, optimal virtual exposure image constructed according to information entropy criterion. Then, latent low-rank representation applied two generate low-ranking parts saliency reduce noise after fusion. Next, initial weight map contained in decomposed images, adaptive refined proposed restore as much structural possible keep details while avoiding halo artifacts. When solving maps, decomposition optimization nonlinear problem converted into a total variation model, iterative method used computational complexity. Last, normalized obtain enhanced image. experimental results showed that performed well both subjective objective evaluation state-of-the-art