Synthesis of High-Resolution Facial Image Based on Top-Down Learning

  • Bon-Woo Hwang
  • Jeong-Seon Park
  • Seong-Whan Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


This paper proposes a method of synthesizing a high-resolution facial image from a low-resolution facial image based on top-down learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in an given low-resolution facial image, we can estimate optimal coeficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be synthesized by using the optimal coeficients for linear combination of the high-resolution prototypes. The encouraging results of the proposed method show that our method can be used to increase the performance of the face recognition by applying our method to enhance the low-resolution facial images captured at surveillance systems.


Face Recognition Facial Image Input Face Bicubic Interpolation Reference Face 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Tom, B., Katsaggelos, A.K.: Resolution Enhancement Monochrome and Color Video Using Motion Comensation. IEEE Trans. on Image Processing, Vol. 10, No. 2 (Feb. 2001) 278–287zbMATHCrossRefGoogle Scholar
  2. [2]
    Baker, S., Kanade, T.: Limit on Super-Resolution and How to Break Them. IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 24 No. 9 (Sep. 2002) 1167–1183CrossRefGoogle Scholar
  3. [3]
    Windyga, P. S.: Fast impulsive noise removal. IEEE Trans. on Image Processing, Vol. 10, No. 1 (2001) 173–178CrossRefGoogle Scholar
  4. [4]
    Jones, M. J., Sinha, P., Vetter, T., Poggio, T: Top-down learning of low-level vision tasks[brief communication]. Current Biology, Vol. 7 (1997) 991–994CrossRefGoogle Scholar
  5. [5]
    Hwang, B.-W., Lee, S.-W.: Reconstruction of Partially Damaged Face Images Based on aMorphable Face Model. IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 25, No. 3 (2003) 365–372CrossRefGoogle Scholar
  6. [6]
    Beymer, D., Shashua, A., Poggio, T.: Example-Based Image Analysis and Synthesis. AI Memo 1431/CBCL Paper 80, Massachusetts Institute of Technology, Cambridge, MA (Nov. 1993)Google Scholar
  7. [7]
    Vetter, T., Troje, N.E.: Separation of texture and shape in images of faces for image coding and synthesis. Journal of the Optical Society of America A. Vol. 14, No. 9 (1997) 2152–2161CrossRefGoogle Scholar
  8. [8]
    Blanz, V., Romdhani, S., Vetter, T.: Face Identification across Different Poses and Illuminations with a 3D Morphable Model. Proc. of the 5th Int’l Conf. on Automatic Face and Gesture Recognition, Washington, D. C. (2002) 202–207Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Bon-Woo Hwang
    • 1
  • Jeong-Seon Park
    • 2
  • Seong-Whan Lee
    • 2
  1. 1.VirtualMedia, Inc., #1808 Seoul Venture TownSeoulKorea
  2. 2.Center for Artificial Vision ResearchKorea UniversitySeoulKorea

Personalised recommendations