BM3D Denoising Algorithm with Adaptive Block-Match Thresholds

Abstract:

Article Preview

A number of image filtering algorithms based on nonlocal means have been proposed in recent years which take advantage of the high degree of redundancy of any natural image. The block-matching with 3D transform domain collaborative filtering (BM3D) proposed in [1] achieves excellent performance in image denoising. But the choice of shrinkage operator in block-matching step is not discussed, only given the threshold by experience in its related papers. In this work, we introduce an improved version of BM3D with adaptive block-match thresholds. The proposed method firstly seeks the relationship between the Structural Similarity index (SSIM) [2] and match distance in blocks and obtains the data with fine SSIM values. Then, compute the Noise level and Gradient values in blocks of the same block size. Finally, surface fitting is adopted to get a formula which applies weak thresholds for flat blocks and strong thresholds for detail blocks. Experiment results are given to demonstrate the same class of denoising performance with less time-consuming to slightly noisy image and good improvement in denoising performance to seriously noisy image.

Info:

Periodical:

Edited by:

Mohamed Othman

Pages:

1715-1720

Citation:

Y. S. Zhang et al., "BM3D Denoising Algorithm with Adaptive Block-Match Thresholds", Applied Mechanics and Materials, Vols. 229-231, pp. 1715-1720, 2012

Online since:

November 2012

Export:

Price:

$38.00

[1] K. Dabov, A. Foi, V. Katkovnik, K. Egiazarian, et al., Image denoising with block-matching and 3D filtering, in : Pro. SPIE Electronic Imaging: Algorithms and Systems V, Vol. 6064A-30 (2006).

DOI: https://doi.org/10.1117/12.643267

[2] Zhou Wang, Eero P. Simoncelli, Stimulus synthesis for efficient evaluation and refinement of perceptual image quality metrics, in: Human Vision and Electronic Imaging IX, Proc. SPIE, Vol. 5292 (2004).

DOI: https://doi.org/10.1117/12.537129

[3] Qian Chen, Dapeng Wu, Image Denoising by Bounded Block Matching and 3D Filtering, "Elsevier, Vol. 90-9, pp.2778-2783(2010).

DOI: https://doi.org/10.1016/j.sigpro.2010.03.016

[4] Tae Hwan Lee, Byung Cheol Song, Denoising algorithm using sparse 3D transform-domain collaborative filtering and adaptive soft thresholding, in: IEEE 15th International Symposium on Consumer Electronics (2011).

DOI: https://doi.org/10.1109/isce.2011.5973798

[5] M. Buckley, Fast computation of a discretized thin-plate smoothing spline for image data, Biometrika, Vol. 81-2, (1994).

DOI: https://doi.org/10.2307/2336955

[6] Information on http: /www. biomecardio. com/matlab/evar. html.

[7] K. Dabov, A. Foi, V. Katkovnik and K. Egiazarian, Image denoising by sparse 3D transform-domain collaborative filtering, IEEE Transactions on image processing, Vol. 16-8 (2007).

DOI: https://doi.org/10.1109/tip.2007.901238