Color Image Restoration Based on Split Bregman Iteration Algorithm
Yi Liya, Xiaolei Lu, Wang FuRong · 2010
In this paper, we modify the Split Bregman algorithm for color image restoration with the edge-preserving color image total variation model. The observed blurred images are assumed to be degraded by within channel and cross channel blurs. Our proposed algorithm is based on the Split Bregman process and simply requires Fast Fourier Transform in each iteration. Experimental comparisons using various types of blurs are reported, and the results show that, the proposed method significantly outperforms existing methods, such as the variable splitting alternative minimization algorithm and that adopted by MATLAB deblurring function, in terms of both objective signal to noise ratio and subjective vision quality. This demonstrates the efficiency of our proposed algorithms.