保持纹理细节的自适应非局部均值图像降噪

doi:10.3969/j.issn.1007-2861.2013.07.023

Journal of Shanghai University（Natural Science Edition） ›› 2014, Vol. 20 ›› Issue (1): 99-106.doi: 10.3969/j.issn.1007-2861.2013.07.023

• Communication and Information Engineering • Previous Articles Next Articles

Adaptive Nonlocal Means Image Denoising for Better Preservation of Textures

CHEN Gang, QIAN Zhen-xing, WANG Shuo-zhong

School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China

Received:2013-02-06 Online:2014-02-28 Published:2014-02-28

Abstract

Abstract: The principal neighborhood dictionaries (PND) nonlocal means (NLM) is an effective method for image denoising, which is based on principal component analysis(PCA). However, it does not make full use of the image contents and is less effective in texture regions. This paper proposes modification to the PND method by adjusting a filter parameter h to achieve better accuracy. Experimental results show that the proposed outperforms PND method and can preserve more edge and texture details while achieving satisfactory denoising results.

Key words: filter parameter, nonlocal means (NLM) denoising, principal component analysis(PCA), principal neighborhood dictionaries (PND)

CLC Number:

TP 391

CHEN Gang, QIAN Zhen-xing, WANG Shuo-zhong. Adaptive Nonlocal Means Image Denoising for Better Preservation of Textures[J]. Journal of Shanghai University（Natural Science Edition）, 2014, 20(1): 99-106.

References

[1] 王锐玲, 施俊. 结合Tetrolet与主动随机场模型的高斯噪声抑制[J]. 上海大学学报: 自然科学版, 2012, 30(3): 275-280.

[2] Buades A, Coll B, Morel J. A review of image denoising algorithms [J]. Multiscale Modeling and Simulation, 2005, 4(2): 490-530.

[3] Buades A, Coll B, Morel J. A non-local algorithm for image denoising [C]//IEEE Conference on Computer Vision and Pattern Recognition. 2005: 60-65.

[4] Kervrann C, Boulanger J, Coupe P. Bayesian nonlocal means filter, image redundancy and adaptive dictionaries for noise removal [J]. Scale Space Methods Variational Methods in

Computer Vision, 2007, 4485: 520-532.

[5] Deledalle C, Denis L, Tupin F. Iterative weighted maximum likelihood denoising with probabilistic patch-based weights [J]. IEEE Transactions on Image Processing, 2009, 18(12): 2661-2672.

[6] Tasdizen T. Principal components for non-local means image denoising [C]//IEEE International Conference on Image Processing. 2008: 1728-1731.

[7] Tasdizen T. Principal neighborhood dictionaries for nonlocal means image denoising [J]. IEEE Transactions on Image Processing, 2009, 18(12): 2649-2660.

[8] van de Ville D, Kocher M. SURE-based nonlocal means [J]. IEEE Signal Process Letters, 2009, 16(11): 973-976.

[9] Salmon J. On two parameters for denoising with nonlocal means [J]. IEEE Signal Process Letters, 2010, 17(3): 269-272.

[10] Yan R, Shao L. Improved nonlocal means based on pre-classification and invariant block matching [J]. IEEE Transactions on Display Technology, 2012, 8(4): 212-218.

[11] 赖新平, 胡海平. 基于各向异性扩散的降噪新方法[J]. 上海大学学报: 自然科学版, 2009, 15(4): 346-350.

[12] Esbensen K, Geladi P. Principal component analysis [C]//Proceedings of the Multivariate Statistical Workshop for Geologists and Geochemists. 1987: 37-52.

[13] Wang S, Lu X, Su S. Image block feature vectors based on a singular-value information metric and color-texture description [J]. Journal of Shanghai University: English Edition, 2007, 11(3): 205-209.

Adaptive Nonlocal Means Image Denoising for Better Preservation of Textures

PDF

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 1

Recommended Articles

Metrics

Comments