Image Denoising Using Nonseparable Wavelet and SURE-LET

In this paper, we present a novel method to image denoising using non-separable wavelet based SURE-LET approach. Unlike conventional separable wavelet filter banks that limit the ability in capturing directional information, non-separable wavelet filter banks contain the basis elements oriented at a variety of directions which are able to capture different detail information. Using SURE-LET makes it needless to hypothesize a statistical model for the noiseless image. Besides, SURE-LET denoising algorithm merely amounts to solving linear system of equations, which is obviously fast and efficient. Experimental results on several test images are compared with separable wavelet based denoising techniques, the competitive results show that the non-separable wavelet based SURE-LET method is effective.