A New Super-Resolution Reconstruction Algorithm Based on Block Sparse Representation

Abstract:

In this paper, we propose a new single super-resolution (SR) reconstruction algorithm via block sparse representation and regularization constraint. Firstly, discrete K-L transform is used to learn compression sub-dictionary according to the specific image block. Combined with threshold choice of training data, the transform bases are generated adaptively corresponding to the sparse domain. Secondly, Non-local Self-similarity (NLSS) regularization term is introduced into sparse reconstruction objective function as a prior knowledge to optimize reconstruction result. Simulation results validate that the proposed algorithm achieves much better results in PSNR and SSIM. It can both enhance edge and suppress noise effectively, which proves better robustness.

• Periodical: Advanced Materials Research (Volume 710)
• Pages: 603-607
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.710.603
• Online since: June 2013
• Authors: Xiao Dong Zhao, Jian Zhong Cao, Hui Zhang, Guang Sen Liu, Hua Wang, Qing Liu
• Keywords: Block Sparse Representation, Discrete K-L Transform, Non-Local Self-Similarity, Super-Resolution

References

[1] J. Yang, J. Wright, T. Huang and Y. Ma, Image super-resolution as sparse representation of raw image patches [J], IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008, p.1~8.

DOI: 10.1109/cvpr.2008.4587647

[2] J. Pu, J P. Zhang, Super-resolution through dictionary learning and sparse representation [J], Pattern Recognition and Artificial Intelligence, 2010, 23(3):335~340. (In Chinese)

[3] Y B. Sun, Z H. Wei, L. Xiao and Z R. Zhang, Fast image super-resolution reconstruction algorithm using sparse representations [J], Systems Engineering and Electronics, 2010, 32(12):2696~2700. (In Chinese)

[4] M. Aharon, M. Elad and A. Bruckstein, K-SVD: an algorithm for designing over-completed dictionaries for sparse representation [J], IEEE Trans. Signal Process, vol.54, no.11, Nov.2006, p.4311~4322.

DOI: 10.1109/tsp.2006.881199

[5] W S. Dong, G M. Shi, L. Zhang and X L. Wu, Super-resolution with Nonlocal Regularized Sparse Representation [J], Proc. SPIE, Vol.7744, 77440H (2010).

[6] A. Buades, B. Coll and J M. Morel, A Review of Image Denoising Algorithms with a New One [J], Multiscale Modeling & Simulation, 2005, 4(2): 490-530.

DOI: 10.1137/040616024

[7] S. Dai, M. Han, W. Xu, Y. Wu, Y. Gong and A.K. Katsaggelos, SoftCuts: a soft edge smoothness prior for color image super-resolution [J], IEEE Trans. Image Process., vol.18, no.5, pp.969-981, May 2009.

DOI: 10.1109/tip.2009.2012908