A regularized mixed norm multichannel image restoration approach

We develop a deterministic regularized mixed norm multichannel image restoration algorithm. A functional which combines the least mean squares (LMS), the least mean fourth (LMF), and a smoothing functional using both within- and between-channel deterministic information is proposed. One parameter is defined to control the relative contribution between the LMS and the LMF norms, and a second one (regularization parameter) is defined to control the degree of smoothness of the solution. They are both updated at each iteration step. The novelty of the proposed algorithm is that no knowledge about the noise distribution for each channel is required, and the parameters are adjusted based on the partially restored image.