Low-Rank Combined Adaptive Sparsifying Transform for Blind Compressed Sensing Image Recovery

HE Ning; WANG Ruolin; LYU Jiayi; XUE Jian

doi:10.1049/cje.2020.05.014

Volume 29 Issue 4

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2020 > 29(4): 678-685

HE Ning, WANG Ruolin, LYU Jiayi, et al., “Low-Rank Combined Adaptive Sparsifying Transform for Blind Compressed Sensing Image Recovery,” Chinese Journal of Electronics, vol. 29, no. 4, pp. 678-685, 2020, doi: 10.1049/cje.2020.05.014

Citation:

HE Ning, WANG Ruolin, LYU Jiayi, et al., “Low-Rank Combined Adaptive Sparsifying Transform for Blind Compressed Sensing Image Recovery,” Chinese Journal of Electronics, vol. 29, no. 4, pp. 678-685, 2020, doi: 10.1049/cje.2020.05.014

Citation:

PDF( 6324 KB)

Low-Rank Combined Adaptive Sparsifying Transform for Blind Compressed Sensing Image Recovery

doi: 10.1049/cje.2020.05.014

1.
Beijing Union University, Beijing 100101, China;
2.
Logistics Department of Beijing Military Region, Beijing 100042, China;
3.
Capital Normal University, Beijing 100048, China;
4.
University of Chinese Academic of Sciences, Beijing 100049, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61572077, No.61872042, No.61370138, No.61671426, No.61731022); the Project of Oriented Characteristic Disciplines (No.KYDE40201701); Joint Research Fund in Astronomy under cooperative agreement between the National Natural Science Foundation of China (NSFC) and Chinese Academy of Sciences (CAS) (No.U1531242); the Beijing Natural Science Foundation (No.4182071); and the Innovation Practice Training Program for College Students of Chinese Academy of Sciences.

Received Date: 2018-12-14
Rev Recd Date: 2019-02-26
Publish Date: 2020-07-10

Abstract

Abstract

Compressed sensing (CS) exploits the sparsity of images or image patches in a transform domain or synthesis dictionary to reconstruct images from undegraded images. Because the synthesis dictionary learning methods involves NP-hard sparse coding and expensive learning steps, sparsifying transform based blind compressed sending (BCS) has been shown to be effective and efficient in applications, while also enjoying good convergence guarantees. By minimizing the rank of an overlapped patch group matrix to efficiently exploit the nonlocal self-similarity features of the image, while the sparsifying transform model imposes the local features of the image. We propose a combined low-rank and adaptive sparsifying transform (LRAST) BCS method to better represent natural images. We utilized the patch coordinate (PCD) descent algorithm to optimize the method, and this enforced the intrinsic local sparsity and nonlocal self-similarity of the images simultaneously in a unified framework. The experimental results indicated a promising performance, even in comparison to state-of-theart methods.
- Low-rank,
- Sparsifying transform,
- Blind compressed sensing (BCS),
- Patch coordinate descent (PCD),
- Image recovery

FullText(HTML)

References(27)

References

D. L. Donoho, “Compressed sensing”, IEEE Transactions on Information Theory, Vol.52, No.4, pp.1289-1306, 2006.

E. J. Candes, T. Tao, “Near optimal signal recovery from random projections: Universal encoding strategies?”, IEEE Transactions on Information Theory, Vol.52, No.12, pp.5406-5424, 2006.

S. Ravishankar and Y. Bresler, “Data-driven learning of a union of sparsifying transforms model for blind compressed sensing”, IEEE Transactions on Computational Imaging, Vol.2, No.3, PP.294-309, 2015.

B. Wen, S. Ravishankar and Y. Bresler, “Learning flipping and rotation invariant sparsifying transforms”, IEEE International Conference on Image Processing (ICIP), pp.3857-3861, 2016.

S. Ravishankar and Y. Bresler, “Efficient blind compressed sensing using sparsifying transforms with convergence guarantees and application to MRI”, SIAM Journal on Imaging Sciences, Vol.8, No.4, pp.2519-2557, 2015.

W. Dong, G. Shi, X. Li, Y. Ma and F. Huang, “Compressive sensing via nonlocal low-rank regularization”, IEEE Transactions on Image Processing, Vol.23, No.8, pp.3618-3632, 2014.

B. Wen, Y. Li, L. Pfister and Y. Bresler, “Joint adaptive sparsity and low-rankness on the fly: An online tensor reconstruction scheme for video denoising”, IEEE International Conference on Computer Vision (ICCV), pp.241-250, 2017.

N. He and Ke Lu, “A non local feature-preserving strategy for image denoising”, Chinese Journal of Electronics, Vol.21, No.4, pp.651-656, 2012.

W. P. Li, K. Deng and F.H. Yu, “Feature-based trajectory privacy preserving via low-rank and sparse decomposition”, Chinese Journal of Electronics, Vol.27, No.4, pp.746-755, 2017.

B. Wen, Y. Li and Y. Bresler, “When sparsity meets low-rankness: Transform learning with non-local lowrank constraint for image restoration”, IEEE International Conference on Speech and Signal Processing (ICASSP), pp.2297-2310, 2017.

S. Ravishankar and Y. Bresler, “Blind compressed sensing using sparsifying transforms”, International Conference on Sampling Theory and Applications (SampTA), pp.513-517, 2015.

S. Ravishankar and Y. Bresler, “Learning sparsifying transforms for image processing”, IEEE International Conference on Image Processing, pp.681-684, 2012.

S. Ravishankar, Bihan Wen and Y. Bresler, “Online sparsifying transform learning-Part I: Algorithms”, IEEE Journal of Selected Topics in Signal Processing, Vol.9, No.4, pp.625-636, 2015.

E. J. Candes, “The restricted isometry property and its implications for compressed sensing”, Comptes Rendus Mathematique, Vol.346, No.9-10, pp.589-592, 2008.

S. Ravishankar and Y. Bresler, “Closed-form solutions within sparsifying transform learning”, IEEE International Conference on Acoustics, Speech and Signal Processing, pp.5378-5382, 2013.

S. Ravishankar, Y. Bresler, “Learning doubly sparsifying transforms for images”, IEEE Transactions on Image Processing, Vol.22, No.12, pp.4598-4612, 2013.

S. Ravishankar and Y. Bresler, “Sparsifying transform learning for compressed sensing MRI”, Proceedings of the 10th International Symposium on Biomedical Imaging, pp.17-20, 2013.

S. Ravishankar and Y. Bresler, “Learning sparsifying transform. IEEE Transactions on Signal Processing”, Vol.61, No.5, pp.1072-1086, 2013.

C. Fu, X. Ji and Q. Dai, “Adaptive compressed sensing recovery utilizing the property of signal's autocorrelations”, IEEE Transactions on Image Processing, Vol.21, No.5, pp.2369-2378, 2012.

Q. Guo, S. Gao, X. Zhang, Y. Yin and C. Zhang, “Patch-based image inpainting via two-stage low rank approximation”, IEEE Transactions on Visualization and Computer Graphics, Vol.24, No.6, pp.2023-2036, 2018.

Y. Xu and W. Yin, “A patch coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion”, SIAM Journal on Imaging Sciences, Vol.6, No.3, pp.1758-1789, 2013.

J. Zhang, C. Zhao, D. Zhao and W. Gao, “Image compressive sensing recovery using adaptively learned sparsifying basis via L₀ minimization”, Computer Vision and Pattern Recognition, Vol.103, pp.114-126, 2014.

L. Gan, T. T. Do and T. D. Tran, “Fast compressive imaging using scrambled patch Hadamard ensemble”, 2008 16th European Signal Processing conference, 2008.

F. Luisier and T. Blu, “SURE-LET multichannel image denoising: Interscale orthonormal wavelet thresholding”, IEEE Transactions on Image Processing, Vol.17, No.4, pp.482-492, 2008.

K. Dabov, A. Foi, V. Katkovnik and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering”, IEEE Transactions on Image Processing, Vol.16, No.8, pp.2080-2095, 2007.

N. Pierazzo and G. Facciolo, “Data adaptive dual domain denoising: A method to boost state of the art denoising algorithms”, Image Processing On Line, 2017.

M. Tassano, J. Delon and T. Veit, “An analysis and implementation of the FFDNet image denoising method”, Image Processing On Line preprint, 2018.

Relative Articles

Supplements(0)

Cited By

Proportional views