Principal Neighborhood Dictionaries for Nonlocal Means Image Denoising

被引:203
作者
Tasdizen, Tolga [1 ,2 ]
机构
[1] Univ Utah, Dept Elect & Comp Engn, Salt Lake City, UT 84112 USA
[2] Univ Utah, Sci Comp & Imaging Inst, Salt Lake City, UT 84112 USA
基金
美国国家科学基金会; 美国国家卫生研究院;
关键词
Image denoising; nonlocal means (NLM); parallel analysis; principal component analysis; principal neighborhood; NUMBER; SCALE; EIGENVALUES; SHRINKAGE; SPARSE;
D O I
10.1109/TIP.2009.2028259
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
We present an in-depth analysis of a variation of the nonlocal means (NLM) image denoising algorithm that uses principal component analysis (PCA) to achieve a higher accuracy while reducing computational load. Image neighborhood vectors are first projected onto a lower dimensional subspace using PCA. The dimensionality of this subspace is chosen automatically using parallel analysis. Consequently, neighborhood similarity weights for denoising are computed using distances in this subspace rather than the full space. The resulting algorithm is referred to as principal neighborhood dictionary (PND) nonlocal means. We investigate PND's accuracy as a function of the dimensionality of the projection subspace and demonstrate that denoising accuracy peaks at a relatively low number of dimensions. The accuracy of NLM and PND are also examined with respect to the choice of image neighborhood and search window sizes. Finally, we present a quantitative and qualitative comparison of PND versus NLM and another image neighborhood PCA-based state-of-the-art image denoising algorithm.
引用
收藏
页码:2649 / 2660
页数:12
相关论文
共 40 条
[1]
[Anonymous], 2001, METHODS PSYCHOL RES, V6, P141
[2]
[Anonymous], P IEEE INT C IM PROC
[3]
[Anonymous], P SPIE ELECT IMAGING
[4]
Unsupervised, information-theoretic, adaptive image filtering for image restoration [J].
Awate, SP ;
Whitaker, RT .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (03) :364-376
[5]
AWATE SP, 2006, P EUR C COMP VIS, P494
[6]
Efficient nonlocal means for denoising of textural patterns [J].
Brox, Thomas ;
Kleinschmidt, Oliver ;
Cremers, Daniel .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2008, 17 (07) :1083-1092
[7]
A non-local algorithm for image denoising [J].
Buades, A ;
Coll, B ;
Morel, JM .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2005, :60-65
[8]
Cates J, 2008, LECT NOTES COMPUT SC, V5241, P477, DOI 10.1007/978-3-540-85988-8_57
[9]
Efros A. A., 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision, P1033, DOI 10.1109/ICCV.1999.790383
[10]
Image denoising via sparse and redundant representations over learned dictionaries [J].
Elad, Michael ;
Aharon, Michal .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (12) :3736-3745