Image super-resolution based on multi-space sparse representation
Sparse representation provides a new method of generating a super-resolution image from a single low resolution input image. An over-complete base for sparse representation is an essential part of such methods. However, discovering the over-complete base with efficient representation from a large amount of image patches is a difficult problem. In this paper, we propose a super-resolution construction based on multi-space sparse representation to efficiently solve the problem. In the representation, image patches are decomposed into a structure component and a texture component represented by the over-complete bases of their own spaces so that their high-level features can be captured by the bases. In the implementation, a prior knowledge about low resolution images generation is combined to the typical base construction for high construction quality. Experiment results demonstrate that the proposed method significantly improves the PSNR, SSIM and visual quality of reconstructed high-resolution image.
KeywordsSuper-resolution Sparse representation Total variation Over-complete bases
This paper is supported by 973 Program (2011CB302703), NSFC (No. 61033004, 60825203, 60973056, 61170103, U0935004, 61003182), BJNSF (4102009, 4112007).
- 3.Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image impainting. Proceeding ACM SIGGRAPH, New Orleans, LA,(July 2000) pp:417–424Google Scholar
- 4.Cai JF, Hui J, Liu CQ, Shen ZW (2009) Blind motion deblurring from a single image using sparse approximation. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, (Jun. 2009)Google Scholar
- 5.Candes E (2006) Compressive sensing. Proceeding International Congress of Mathematicians, (2006)Google Scholar
- 7.Capel D, Zisserman A (2001) Super-resolution from multiple views using learnt image models. Proc IEEE Conf Comput Vis Pattern Recognit 2(II):627–634Google Scholar
- 11.Irani M, Peleg S (1991) Improving resolution by image restoration. CVGIP: Graph Models Image Process 53:231–239Google Scholar
- 12.Landgrebe TCW, Duin RPW (2008) Efficient multi-class ROC approximation by decomposition via confusion matrix perturbation analysis. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol: 30, Issue: 5, (May 2008) pp: 810 vol. 2Google Scholar
- 13.Lee H, Battle A, Raina R, Ng AY (2006) Efficient sparse coding algorithms. NIPS, (2006)Google Scholar
- 17.Sun J, Zheng NN, Tao H, Shum HY (2003) Image Hallucination with Primal Sketch Priors. Proc IEEE Conf Comput Vis Pattern Recognit 2(II):729–736Google Scholar
- 18.Yang JC, John W, Ma Y, Huang T (2008) Image super-resolution as a sparse representation of raw image patches. Proc IEEE Conf Comput Vis Pattern Recognit, Anchorage, Alsk 2008:333–340Google Scholar
- 20.Yang J, Zhang Y (2009) Alternating direction algorithms for L1-problems in compressive sensing. Rice University CAAM Technical Report, (2009) TR09-37Google Scholar