Image denoising based on Non-Local means and multi-scale dyadic wavelet transform
Gang Yu, Yong Yin, Hongjun Wang, Zhi Liu, Dengwang Li · 2010
A variety of wavelet transform methods have been introduced to remove noise from images. However, many of these algorithms remove the fine details and smooth the structures of the image when removing noise. The wavelet coefficient magnitude sum (WCMS) algorithm can preserve edges, but it is at the expense of removing noise. The Non-Local means algorithm can removing noise effective. But it tend to cause distortion ( eg white). Meanwhile, when the noise is large, the method is not so effective. In this paper, we propose an efficient denoising algorithm. we denoised the image with non-local means algorithm in the spatial domain and WCMS algorithm in wavelet domain, weighted, combined them and got the image that we want. The experiment shows that our algorithm can improve PSNR form 0.6 dB to 1.0 dB and the image boundary is more clearly.