Skip to main content
SpringerLink
Log in

Face Hallucination via Trend-Constrained Regularization

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

Sparse representation based face hallucination methods only utilize generic sparsity prior irrespective of the fact that the near bases in dictionary do make a greater contribution to patch reconstruction. Consequently, they cannot provide satisfactory hallucinated results in terms of accuracy and noise robustness. In this paper, instead of modifying the existing ℓ 1 norm regularization, we propose a completely novel trend-constrained regularization method by exploiting a priori known as shape trend regarding coefficient and similarity curves. In particular, this method explicitly encourages the unknown coefficient curve to follow the shape variation trend of a predetermined similarity curve by means of maximizing their correlation. Owning to the differentiability of the underlying model, both the solution and regularization parameter can be analytically tractable, thus avoiding complex numerical optimization. Based on the observation on distance statistics, we further devise two optimal similarity functions in the form of power and exponential kernel functions. The proposed method boosts face hallucination performance considerably compared with the state-of-the-art methods. Experiments on commonly used face database demonstrate its effectiveness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5

Similar content being viewed by others

References

  1. Baker, S., & Kanade, T. (2002). Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(9), 1167–1183.

    Article  Google Scholar 

  2. Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323–2326.

    Article  Google Scholar 

  3. Chang, H., Yeung, D. Y., & Xiong, Y. M. (2004). Super-resolution through neighbor embedding. In IEEE Conference on Computer Vision and Pattern Recognition, (pp. 275–282).

  4. Ma, X., Zhang, J., & Qi, C. (2010). Hallucinating face by position-patch. Pattern Recognition, 43(6), 3178–3194.

    Article  Google Scholar 

  5. Candès, E. J., Romberg, J., & Tao, T. (2006). Stable signal recovery from incomplete and inaccurate measurements. Communications on Pure and Applied Mathematics, 59, 1207–1223.

    Article  MATH  MathSciNet  Google Scholar 

  6. Farsiu, S., Robinson, M. D., & Elad, M. (2006). Fast and robust multiframe super-resolution. IEEE Transactions on Image Processing, 15(1), 141–159.

    Article  Google Scholar 

  7. Zou, H., & Hastie, T. (2005). Regression shrinkage and selection via the elastic net, with applications to microarrays. Journal of the Royal Statistical Society, Series B, 67, 301–320.

    Article  MATH  MathSciNet  Google Scholar 

  8. Yang, J., Tang, H., Ma, Y., & Huang, T. (2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing, 19(11), 2861–2873.

    Article  MathSciNet  Google Scholar 

  9. Jung, C., Jiao, L., Liu, B., & Gong, M. (2011). Position-patch based face hallucination using convex optimization. IEEE Signal Processing Letter, 18(6), 367–370.

    Article  Google Scholar 

  10. Yu, K., Zhang, T., & Gong, Y. (2009). Nonlinear learning using local coordinate coding. In Proceedings of Advances in Neural Information Processing Systems, (pp. 2223–2231).

  11. Friedlander, M. P., Mansour, H., Saab, R., & Yilmaz, O. (2012). Recovering compressively sampled signals using partial support information. IEEE Transactions on Information Theory, 58(2), 1122–1134.

    Article  MathSciNet  Google Scholar 

  12. Jiang, J., Hu, R., Han, Z., Lu, T., & Huang, K. (2012). Position-patch based face hallucination via locality-constrained representation. In IEEE International Conference on Multimedia & Expo, (pp. 212–217).

  13. Zhang, K., Gao, X., Tao, D., & Li, X. (2012). Single image super-resolution with non-local means and steering kernel regression. IEEE Transactions on Image Processing, 21(11), 4544–4556.

    Article  MathSciNet  Google Scholar 

  14. Dong, W., Zhang, L., Shi, G., & Li, X. (2013). Nonlocally centralized sparse representation for image restoration. IEEE Transactions on Image Processing, 22(4), 1620–1630.

    Article  MathSciNet  Google Scholar 

  15. Xiaoqiang, L., Yuan, Y., & Yan, P. (2014). Alternatively constrained dictionary learning for image super-resolution. IEEE Transactions on Cybernetics, 44(3), 366–377.

    Article  Google Scholar 

  16. Jiang, J., Hu, R., Wang, Z., Xiong, Z., & Han, Z. (2013). Support-driven sparse coding for face hallucination. In IEEE International Symposium on Circuits and Systems, (pp. 2980–2983).

  17. Bose, N. K., Lertrattanapanich, S., & Koo, J. (2001). Advances in super-resolution using L-curve. In IEEE International Symposium on Circuits and Systems, (pp. 433–436).

  18. Nguyen, N., Milanfar, P., & Golub, G. (2001). A computationally efficient super resolution image reconstruction algorithm. IEEE Transactions on Image Processing, 10(3), 573–583.

    Article  MATH  MathSciNet  Google Scholar 

  19. FEI Face Database (2012), Available at http://fei.edu.br/~cet/facedatabase.html.

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China (61070080, 61170023, 61172173, 61231015, 61303114, 61172174, 61302111), the Major National Science and Technology Special Projects (2010ZX03004-003-03, 2012YQ16018505, 2013BAH42F03), and the Fundamental Research Funds for the Central Universities (2042014kf0286, 2042014kf0212, 2042014kf0025, 2042014kf0250).

Author information

Authors and Affiliations

  1. National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University, Wuhan, 430079, China

    Zhongyuan Wang, Zhen Han & Jinhui Hu

  2. China Electronics Technology Group Corporation NO.38 Institute, Hefei, 230088, China

    Qijun Wang

Authors
  1. Zhongyuan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhen Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qijun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinhui Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhongyuan Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Z., Han, Z., Wang, Q. et al. Face Hallucination via Trend-Constrained Regularization. J Sign Process Syst 79, 105–111 (2015). https://doi.org/10.1007/s11265-014-0941-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-014-0941-9

Keywords

Search

Navigation