Research and Optimization on BM3D Denoising Algorithm

Article Preview

Abstract:

By grouping up the similar blocks in the picture and Collaborative Filtering, BM3D gets a good denoising effect. But denoising performance declined when the noise enhanced. A reason of poor denoising effect in strong noise was put forward in this paper. Then the denoising ability of BM3D was enhanced by optimizing the parameters.BM3D is proved superior to the traditional filtering denoising algorithm and the optimized BM3D gets a better effect than the original one in strong noise in simulation.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

3976-3979

Citation:

Online since:

September 2014

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Kostadin, Dabov. Image Denoising by Sparse 3-D Transform-Domain[J]. IEEE TRANSACTIONS ON IMAGEPROCESSING, 2007, 16(8): 2080-(2095).

DOI: 10.1109/tip.2007.901238

Google Scholar

[2] Dabov K, Foi A, Katkovnik V, et al. A nonlocal and shape-adaptive transform-domain collaborative filtering. Proceedings of International Workshop Local and Non-Local Approximation Image Processing, 2008, 179-186.

DOI: 10.1109/lnla.2009.5278404

Google Scholar

[3] Dabov K, Foi A, Katkovnik V, et al. BM3D image denoising with shape-adaptive principal component analysis. Proceedings of Workshop on Signal Processing with Adaptive Sparse Structured Representations, 2009, 221-226.

Google Scholar

[4] Xiangle Liu, Xiangchu Feng. Image denoising by mixing wavelet transformation with sparse 3D collaborative filtering[J]. COMPUTER ENGINEERING AND APPLICATIONS, 2010, 46(16): 185-187.

Google Scholar

[5] Yingkun Hou. Research on Nonlocal Transform Domain Image Denoising and Enhancement and Their Performance Evaluation[D], Nanjin: Nanjin University of Science and Technology, (2012).

Google Scholar