Color image denoising based on multichannel non-local means fusion

In this paper, we investigate the problem of color image denoising, and propose a novel algorithm called multichannel non-local means fusion (MNLMF), building on the grayscale denoiser non-local means filter. By analyzing and modeling the inter-channel correlation in color images, we formulate the color noise reduction as a minimization problem with a specifically-designed penalty function which fully takes advantages of the inter-channel prior information. The optimal solution is derived consisting of constructing multiple non-local means spanning all three channels and fusing them together. The weights in the fusion are optimized to minimize the overall denoising error. Simulation results under various noise levels demonstrate that when compared to other state-of-the-art algorithms, the proposed MNLMF achieves competitive performance both in terms of the color peak signal-to-noise ratio (cPSNR) and in perceptual quality.