Image super-resolution based on multi-space sparse representation

详细信息    查看全文

• 作者：Guodong Jing (1)
  Yunhui Shi (1)
  Dehui Kong (1)
  Wenpeng Ding (1)
  Baocai Yin (1)
  
• 关键词：Super ; resolution ; Sparse representation ; Total variation ; Over ; complete bases
• 刊名：Multimedia Tools and Applications
• 出版年：2014
• 出版时间：May 2014
• 年：2014
• 卷：70
• 期：2
• 页码：741-755
• 全文大小：
• 参考文献：1. Alfonso S, Gonzalo P (2008) Noniterative interpolayion-based super-resolution minimizing aliasing in the reconstructed image. IEEE Trans Image Process 17(10):1817鈥?826 CrossRef
  2. Baker S, Kanade T (2002) Limits of super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24:1167鈥?183 CrossRef
  3. Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image impainting. Proceeding ACM SIGGRAPH, New Orleans, LA,(July 2000) pp:417鈥?24
  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)
  5. Candes E (2006) Compressive sensing. Proceeding International Congress of Mathematicians, (2006)
  6. Candes EJ, Wakin MB (2008) An introduction to compressive sampling. IEEE Signal Process Mag 25(2):21鈥?0 CrossRef
  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鈥?34
  8. Dong W, Zhang L, Shi G, Wu X (2011) Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization. IEEE Trans Image Process PP(99):1
  9. Elad M, Aharon M (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15(12):3736鈥?745 CrossRef
  10. Herman MA, Strohmer T (2009) High-resolution radar via compressed sensing. IEEE Trans Signal Process 57:2275鈥?284 CrossRef
  11. Irani M, Peleg S (1991) Improving resolution by image restoration. CVGIP: Graph Models Image Process 53:231鈥?39
  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. 2
  13. Lee H, Battle A, Raina R, Ng AY (2006) Efficient sparse coding algorithms. NIPS, (2006)
  14. Li X, Orchard MT (2001) New edge-directed interpolation. IEEE Trans Image Process 10(10):1521鈥?527 CrossRef
  15. Rauhut H, Schnass K, Vandergheynst P (2008) Compressed sensing and redundant dictionaries. IEEE Trans Inf Theory 54:2210鈥?219 CrossRef
  16. Schultz R, Stevenson R (1996) Extraction of highresolution frames from video sequences. IEEE Trans Image Process 5:996鈥?011 CrossRef
  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鈥?36
  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鈥?40
  19. Yang JC, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19:2861 CrossRef
  20. Yang J, Zhang Y (2009) Alternating direction algorithms for L1-problems in compressive sensing. Rice University CAAM Technical Report, (2009) TR09-37
  21. Zhang L, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE Trans Image Process 15(8):2226鈥?238 CrossRef
  22. Zhang X, Wu W (2008) Image interpolation by adaptive 2D autoregressive modeling and soft-decision estimation. IEEE Trans Image Process 17(6):887鈥?96 CrossRef
  
• 作者单位：Guodong Jing (1)
  Yunhui Shi (1)
  Dehui Kong (1)
  Wenpeng Ding (1)
  Baocai Yin (1)
  
  1. Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology, College of Computer Science and Technology, Beijing University of Technology, Beijing, 100124, China
  
• ISSN：1573-7721

文摘

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.