Skip to main content
SpringerLink
Log in

Face image super-resolution via sparse representation and wavelet transform

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Increasing the quality of low-resolution images, namely super-resolution, has recently received a lot of attention in the field of image processing. Super-resolution has various applications, especially in the context of face recognition. Single-image super-resolution via sparse representation is the main issue of our proposed algorithm. A challenging problem in previous algorithms of super-resolution based on sparse representation is output images that are blurred and patchy at the boundaries. To overcome this fault, knowing that the distinction between various faces is due to differences in the structure of eyes, lips and nose, we modify the process of creating the dictionaries in sparse representation scheme, by assigning coefficients to selected patches in the dictionary. Moreover, discrete wavelet transform is used to create a new dataset representation in order to retrieve the high-frequency missing details in the sparse representation. The experimental results on standard datasets of face images demonstrate that our proposed method can recover more details from a low-resolution input image, consequently generating better quality outputs. We have compared our results with the results of a recent sparse representation-based super-resolution, bicubic interpolation and back-projection methods, to show the superiority of the proposed method.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Rao, K.S., Koolagudi, S.G.: Recognition of emotions from video using acoustic and facial features. Signal Image Video Process. 9(5), 1029–1045 (2015)

    Article  Google Scholar 

  2. Shi, Z., et al.: Blind multi-image super-resolution based on combination of ANN learning and non-subsampled Contourlet directional image representation. Signal Image Video Process. 12(1), 25–31 (2018)

    Article  Google Scholar 

  3. Nasrollahi, K., Moeslund, T.B.: Super-resolution: a comprehensive survey. Mach. Vis. Appl. 25(6), 1423–1468 (2014)

    Article  Google Scholar 

  4. Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 46–53 (2000)

  5. He, H., Siu, W.C.: Single image super-resolution using Gaussian process regression. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 449–456 (2011)

  6. Tsai, R.Y.: Multiframe image restoration and registration. Adv. Comput. Vis. Image Process. 1(2), 317–339 (1984)

    Google Scholar 

  7. Irani, M., Peleg, S.: Super resolution from image sequences. In: Proceedings of 10th IEEE International Conference on Pattern Recognition, vol. 2, pp. 115–120 (1990)

  8. Baker, S., Kanade, T.: Hallucinating faces. Fourth IEEE International Conference on Automatic Face and Gesture Recognition, 2000. Proceedings, pp. 83–88. IEEE, Washington (2000)

  9. Liu, C., Shum, H.Y., Zhang, C.S.: A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, I-I (2001)

  10. Chang, H., Yeung, D.Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, I-I (2004)

  11. Huang, K., Hu, R., Han, Z., Lu, T., Jiang, J., Wang, F.: Face image superresolution via locality preserving projection and sparse coding. JSW 8(8), 2039–2046 (2013)

    Google Scholar 

  12. Huang, H., He, H., Fan, X., Zhang, J.: Super-resolution of human face image using canonical correlation analysis. Pattern Recognit. 43(7), 2532–2543 (2010)

    Article  MATH  Google Scholar 

  13. Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  14. Lee, D.D., Seung, H.S.: Learning the parts of objects by non-negative matrix factorization. Nature 401(6755), 788–791 (1999)

    Article  MATH  Google Scholar 

  15. Yang, J., Wright, J., Huang, T., Ma, Y.: Image super-resolution as sparse representation of raw image patches. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 1–8 (2008)

  16. Lee, H., Battle, A., Raina, R., Ng, A.Y.: Efficient sparse coding algorithms. In: Advances in Neural Information Processing Systems, vol. 19, pp. 801–808 (2007)

  17. The FERET Database. https://www.nist.gov/programs-projects/face-recognition-technology-feret. Accessed 2 May 2018

  18. Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, I-I (2001)

  19. Demirel, H., Anbarjafari, G.: Discrete wavelet transform-based satellite image resolution enhancement. IEEE Trans. Geosci. Remote Sens. 49(6), 1997–2004 (2011)

    Article  MATH  Google Scholar 

  20. Moon, Y.S.: Super-resolution image reconstruction using wavelet based patch and discrete wavelet transform. J. Signal Process. Syst. 81(1), 71–81 (2015)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Signal and Image Processing Lab, Shiraz, Iran

    Farnaz Fanaee, Mehran Yazdi & Mohammad Faghihi

Authors
  1. Farnaz Fanaee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mehran Yazdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohammad Faghihi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mehran Yazdi.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fanaee, F., Yazdi, M. & Faghihi, M. Face image super-resolution via sparse representation and wavelet transform. SIViP 13, 79–86 (2019). https://doi.org/10.1007/s11760-018-1330-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-018-1330-9

Keywords

Search

Navigation