Abstract
Sparse representation has been proved successful in solving image super-resolution (SR) problems. It aims to compensate the high-frequency details from a pair of high–low (HL) resolution dictionary which is trained by the corresponding resolution of image patches. This paper presents a novel strategy to generate a super-resolution image via multi-stage HL dictionaries which are trained by a cascade training process. Extensive experiments on image super-resolution validate that the proposed solution can get much better results than some state-of-the-arts ones in terms of PSNR and FSIM.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
J. Sun, N. N. Zheng, H. Tao, and H. Shum, “Image hallucination with primal sketch priors,” IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 729–736, 2003.
Z. Xiong, X. Sun, and F. Wu, “Image hallucination with feature enhancement,” IEEE Conference on Computer Vision and Pattern Classification, vol. 1, pp. 2074–2081, 2009.
W. T. Freeman, E. C. Pasztor, and O. T. Carmichael, “Learning low-level vision,” International Journal of Computer Vision, vol. 40, no. 1, pp. 25–47, 2000.
H. Chang, D.-Y. Yeung, and Y. Xiong, “Super-resolution through neighbor embedding,” IEEE Conference on Computer Vision and Pattern Classification, vol. 1, pp. 275–282, 2004.
R. Zeyde, M. Elad, and M. Protter, “On Single Image Scale-Up using Sparse-Representations,” Curves & Surfaces, Avignon France, June, 24–30, 2010.
D. L. Donoho, “Compressed sensing,” IEEE Transactions on Information Theory, vol. 52, no. 4, pp. 1289–1306, 2006.
J. Yang, J. Wright, T. Huang, and Y. Ma, “Image superresolution via sparse representation,” IEEE Trans. on Image Processing, vol. 19, no. 11, pp. 2861–2873, Nov. 2010.
J. Zhang, C. Zhao, S.W. Ma, D.B. Zhao.“Image Super-Resolution via Dual-Dictionary Learning And Sparse Representation”. ISCAS, page 1688–1691. IEEE, (2012).
M. Aharon, M. Elad, and A. Bruckstein, “K-SVD: An algorithm for designing over complete dictionaries for sparse representation,” IEEE Trans. on Signal Processing, vol. 54, no. 11, pp. 4311–4322, Nov. 2006.
Acknowledgements
This work was supported in part by the Canada NSERC Business Intelligence Network and by the University of Waterloo, in part by the National Science and Technology Major Project under Grant 2013ZX01033002-003, in part by the National High Technology Research and Development Program of China (863 Program) under Grant 2013AA014601, in part by the National Science Foundation of China under Grants 61300028, in part by the Project of the Ministry of Public Security under Grant 2014JSYJB009.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, D., Shi, W., Wang, W., Wu, Z., Mei, L. (2018). Multi-stage Dictionary Learning for Image Super-Resolution Based on Sparse Representation. In: Yen, N., Hung, J. (eds) Frontier Computing. FC 2016. Lecture Notes in Electrical Engineering, vol 422. Springer, Singapore. https://doi.org/10.1007/978-981-10-3187-8_10
Download citation
DOI: https://doi.org/10.1007/978-981-10-3187-8_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3186-1
Online ISBN: 978-981-10-3187-8
eBook Packages: EngineeringEngineering (R0)