An Adaptive Iteratively Weighted Half Thresholding Algorithm For Image Compressive Sensing Reconstruction

The L-1/2 regularization has been considered as a more effective relaxation method to approximate the optimal L-0 sparse solution than L-1 in CS. To improve the recovery performance of L-1/2 regularization, this study proposes a multiple sub-wavelet-dictionaries-based adaptive iteratively weighted L-1/2 regularization algorithm (called MUSAI-L-1/2), and considering the key rule of the weighted parameter (or regularization parameter) in optimization progress, we propose the adaptive scheme for parameter lambda(d) to weight the regularization term which is a composition of the sub-dictionaries. Numerical experiments confirm that the proposed MUSAI-L-1/2 can significantly improve the recovery performance than the previous works.