Multimedia Tools and Applications

, Volume 76, Issue 15, pp 16809–16829 | Cite as

A robust face hallucination technique based on adaptive learning method

  • Rohit U.
  • Abdu Rahiman V.
  • Sudhish N. George


Position-patch based approaches have been proposed for single-image face hallucination. This paper models the face hallucination problem as a coefficient recovery problem with respect to an adaptive training set for improved noise robustness. The image-adaptive training set is constructed by corrupting a local training set of position-patches by adding specific amounts of noise depending on the input image noise level. In this proposed method, image denoising and super-resolution are simultaneously carried out to obtain superior results. Though the principle is general and can be extended to most super-resolution algorithms, we discuss this in context of existing locality-constrained representation (LcR) approach in order to compare their performances. It can be demonstrated that the proposed approach can quantitatively and qualitatively yield better results in high noisy environments.


Super-resolution Hallucination Sparse representation Position-patch Regularization 


  1. 1.
    Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Anal Mach Intell 24(9):1167–1183CrossRefGoogle Scholar
  2. 2.
    Chang H, Yeung DY, Xiong Y (2004) Super-resolution through neighbor embedding. In: Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, IEEE, vol 1, pp I–IGoogle Scholar
  3. 3.
    Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3d transform-domain collaborative filtering. IEEE Trans Image Process 16(8)Google Scholar
  4. 4.
    Dong W, Li X, Zhang L, Shi G (2011) Sparsity-based image denoising via dictionary learning and structural clustering. In: Computer vision and pattern recognition (CVPR), 2011 IEEE Conference on, IEEE, pp 457–464Google Scholar
  5. 5.
    Donoho DL, Elad M, Temlyakov VN (2006) Stable recovery of sparse overcomplete representations in the presence of noise. IEEE Trans Inf Theory 52(1):6–18MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Elad M, Aharon M (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process 15(12):3736–3745MathSciNetCrossRefGoogle Scholar
  7. 7.
    Farsiu S, Robinson D, Elad M, Milanfar P (2004) Advances and challenges in super-resolution. Int J Imaging Syst Technol 14(2):47–57CrossRefGoogle Scholar
  8. 8.
    Hardie RC, Barnard KJ, Armstrong EE (1997) Joint map registration and high-resolution image estimation using a sequence of undersampled images. IEEE Trans Image Process 6(12):1621– 1633CrossRefGoogle Scholar
  9. 9.
    Irani M, Peleg S (1993) Motion analysis for image enhancement: resolution, occlusion, and transparency. J Vis Commun Image Represent 4(4):324–335CrossRefGoogle Scholar
  10. 10.
    Jiang J, Hu R, Han Z, Lu T, Huang K (2012) Position-patch based face hallucination via locality-constrained representation. In: Multimedia and expo (ICME), 2012 IEEE International Conference on, IEEE, pp 212–217Google Scholar
  11. 11.
    Jiang J, Hu R, Wang Z, Han Z (2014) Noise robust face hallucination via locality-constrained representation. IEEE Trans Multimedia 16(5):1268–1281CrossRefGoogle Scholar
  12. 12.
    Jin Y, Bouganis CS (2015) Robust multi-image based blind face hallucination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5252–5260Google Scholar
  13. 13.
    Liu C, Shum HY, Freeman WT (2007) Face hallucination: Theory and practice. Int J Comput Vis 75(1):115–134CrossRefGoogle Scholar
  14. 14.
    Liu X, Tanaka M, Okutomi M (2013) Single-image noise level estimation for blind denoising. IEEE Trans Image Process 22(12):5226–5237CrossRefGoogle Scholar
  15. 15.
    Ma X, Zhang J, Qi C (2010) Hallucinating face by position-patch. Pattern Recogn 43(6):2224–2236CrossRefGoogle Scholar
  16. 16.
    Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A (2009) Non-local sparse models for image restoration. In: Computer Vision, 2009 IEEE 12th International Conference on, IEEE, pp 2272–2279Google Scholar
  17. 17.
    Nasrollahi K, Moeslund TB (2014) Super-resolution: a comprehensive survey. Mach Vis Appl 25(6):1423–1468CrossRefGoogle Scholar
  18. 18.
    Park SC, Park MK, Kang MG (2003) Super-resolution image reconstruction: a technical overview. IEEE Signal Process Mag 20(3):21–36CrossRefGoogle Scholar
  19. 19.
    Schultz RR, Stevenson RL (1996) Extraction of high-resolution frames from video sequences. IEEE Trans Image Process 5(6):996–1011CrossRefGoogle Scholar
  20. 20.
    Shao L, Yan R, Li X, Liu Y (2014) From heuristic optimization to dictionary learning: a review and comprehensive comparison of image denoising algorithms. IEEE Trans Cybern 44(7):1001–1013CrossRefGoogle Scholar
  21. 21.
    Singh A, Porikli F, Ahuja N (2014) Super-resolving noisy images. In: Computer vision and pattern recognition (CVPR), 2014 IEEE Conference on, IEEE, pp 2846–2853Google Scholar
  22. 22.
    Thomaz CE (2012) Fei face database.
  23. 23.
    Wang N, Tao D, Gao X, Li X, Li J (2014a) A comprehensive survey to face hallucination. Int J Comput Vis 106(1):9–30Google Scholar
  24. 24.
    Wang Z, Hu R, Wang S, Jiang J (2014b) Face hallucination via weighted adaptive sparse regularization. IEEE Trans Circuits Syst Video Technol 24(5):802–813Google Scholar
  25. 25.
    Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873MathSciNetCrossRefGoogle Scholar
  26. 26.
    Zhang Y (2013) Theory of compressive sensing via l 1-minimization: a non-rip analysis and extensions. J Oper Res Soc China 1(1):79–105CrossRefzbMATHGoogle Scholar
  27. 27.
    Zhou W, Bovik AC, R Sheikh H, P Simoncelli E (2004) Image quality assessment: From error measurement to structural similarity. IEEE Trans Image Process 13(1):1–14Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.National Institute of Technology CalicutCalicutIndia

Personalised recommendations