Open Access

Adaptive Markov Random Fields for Example-Based Super-resolution of Faces

EURASIP Journal on Advances in Signal Processing20062006:031062

Received: 21 December 2004

Accepted: 5 April 2005

Published: 7 February 2006


Image enhancement of low-resolution images can be done through methods such as interpolation, super-resolution using multiple video frames, and example-based super-resolution. Example-based super-resolution, in particular, is suited to images that have a strong prior (for those frameworks that work on only a single image, it is more like image restoration than traditional, multiframe super-resolution). For example, hallucination and Markov random field (MRF) methods use examples drawn from the same domain as the image being enhanced to determine what the missing high-frequency information is likely to be. We propose to use even stronger prior information by extending MRF-based super-resolution to use adaptive observation and transition functions, that is, to make these functions region-dependent. We show with face images how we can adapt the modeling for each image patch so as to improve the resolution.


Authors’ Affiliations

Electrical & Computer Engineering Department, Carnegie Mellon University
ReallaeR, LLC


  1. Jain AK: Fundamentals of Digital Image Processing. Prentice-Hall, Englewood Cliffs, NJ, USA; 1989.MATHGoogle Scholar
  2. Tsai RY, Huang TS: Multiframe image restoration and registration. In Advances in Computer Vision and Image Processing. Volume 1. JAI Press, Greenwich, Conn, USA; 1984:317-339. chapter 7Google Scholar
  3. Schultz RR, Stevenson RL: Extraction of high-resolution frames from video sequences. IEEE Transactions on Image Processing 1996, 5(6):996-1011. 10.1109/83.503915View ArticleGoogle Scholar
  4. Freeman WT, Pasztor EC, Carmichael OT: Learning low-level vision. International Journal of Computer Vision 2000, 40(1):25-47. 10.1023/A:1026501619075MATHView ArticleGoogle Scholar
  5. Li SZ: Markov Random Field Modeling in Image Analysis, Computer Science Workbench Series. Volume 19. Springer, Tokyo, Japan; 2001.View ArticleGoogle Scholar
  6. Pearl J: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Fransisco, Calif, USA; 1988.MATHGoogle Scholar
  7. Baker S, Kanade T: Limits on super-resolution and how to break them. IEEE Transactions on Pattern Analysis and Machine Intelligence 2002, 24(9):1167-1183. 10.1109/TPAMI.2002.1033210View ArticleGoogle Scholar
  8. Dedeoğlu G, Kanade T, August J: High-zoom video hallucination by exploiting spatio-temporal regularities. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '04), June–July 2004, Washington, DC, USA 2: 151-158.Google Scholar
  9. Lauritzen SL: Graphical Models, Oxford Statistical Science Series, No. 17. Clarendon Press, Oxford, UK; 1996.Google Scholar
  10. Schneiderman HW: A statistical approach to 3D object detection applied to faces and cars, M.S. thesis. Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa, USA; May 2000. CMU-RI-TR-00-06Google Scholar
  11. Freeman WT, Jones TR, Pasztor EC: Example-based super-resolution. IEEE Computer Graphics and Applications 2002, 22(2):56-65. 10.1109/38.988747View ArticleGoogle Scholar
  12. Yedidia JS, Freeman WT, Weiss Y: Generalized belief propagation. In Proceedings of Advances in Neural Information Processing Systems 13 (NIPS '00). Volume 13. Edited by: Leen TK, Dietterich TG, Tresp V. MIT Press, Cambridge, Mass, USA; 2001:689-695.Google Scholar
  13. Bishop CM: Neural Networks for Pattern Recognition. Oxford University Press, Oxford, UK; 1995.MATHGoogle Scholar
  14. Phillips PJ, Moon H, Rizvi SA, Rauss PJ: The FERET evaluation methodology for face-recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 2000, 22(10):1090-1104. 10.1109/34.879790View ArticleGoogle Scholar


© T. A. Stephenson and T. Chen 2006

This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.