Natural Image Denoising Using Sparse ICA Based on 2-D Gabor Wavelet

A new natural image denoising method using Sparse Independent Component Analysis (SICA) based on Gabor wavelet is discussed in this paper. In order to maximize the sparsity, SICA algorithm utilizes l^infin norm as the sparse penalty function. At the same time, to insure the speed of SICA, 2-D Gabor wavelet bases are used as the initialization feature bases of SICA. This SICA algorithm does not need optimizing the high-order non-linear functions and density estimation, therefore, it is very simple in computing and its convergent speed is also very quick. The experiment results show that it can successfully extract features of natural images and reduce the Gauss additive noise added artificially in images. Furthermore, compared with other image denoising algorithm used widely, the simulation results also show that our method is indeed reasonable and efficient in denoising natural images.