Hallucinating Faces: Global Linear Modal Based Super-Resolution and Position Based Residue Compensation

  • Xiang Ma
  • Junping Zhang
  • Chun Qi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)


A learning-based face hallucination method is proposed in this paper for the reconstruction of a high-resolution face image from a low-resolution observation based on a set of high- and low-resolution training image pairs. The proposed global linear modal based super-resolution estimates the optimal weights of all the low-resolution training images and a high-resolution image is obtained by applying the estimated weights to the high-resolution space. Then, we propose a position based local residue compensation algorithm to better recover subtle details of face. Experiments demonstrate that our method has advantage over some established methods.


Face hallucination Super-resolution Residue compensation 


  1. 1.
    Baker, S., Kanade, T.: Hallucinating Faces. In: IEEE Inter. Conf. on Automatic Face and Gesture Recognition, pp. 83–88. IEEE Press, France (2000)Google Scholar
  2. 2.
    Liu, C., Shum, H.Y., Zhang, C.S.: A two-step approach to hallucinating faces: global parametric model and local nonparametric model. In: Inter. Conference on Image and Graphics, pp. 192–198. IEEE Press, New York (2001)Google Scholar
  3. 3.
    Chang, H., Yeung, D.-Y., Xiong, Y.: Super-resolution through neighbor embedding. In: Inter. Conference on Computer Vision and Pattern Recognition, pp. 1275–1282. IEEE Press, Washington (2004)Google Scholar
  4. 4.
    Costa, G.H., Bermudez, J.C.M.: Statistical analysis of the LMS algorithm applied to super resolution image reconstruction. IEEE Transactions on Signal Processing 11, 2084–2095 (2007)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Zhuang, Y., Zhang, J., Wu, F.: Hallucinating faces: LPH super-resolution and neighbor reconstruction for residue compensation. Pattern Recognition 40, 3178–3194 (2007)CrossRefzbMATHGoogle Scholar
  6. 6.
    Wang, X., Tang, X.: Hallucinating Face by Eigentransformation. IEEE Transactions on Systems Man and Cybernetics 35, 425–434 (2005)CrossRefGoogle Scholar
  7. 7.
    Gao, W., et al.: The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations. IEEE Transactions on System Man, and Cybernetics (Part A) 38, 149–161 (2008)CrossRefGoogle Scholar
  8. 8.
    Jia, K., Gong, S.G.: Generalized face super-resolution. IEEE Transactions on Image Processing 17, 873–886 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Park, J.S.S., Lee, W.: An Example-Based Face Hallucination Method for Single-Frame, Low-resolution Facial Images. IEEE Transactions on Image Processing 17, 1806–1816 (2008)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Xiang Ma
    • 1
  • Junping Zhang
    • 2
  • Chun Qi
    • 1
  1. 1.School of Electronics& Information EngineeringXi’an Jiaotong UniversityXi’anChina
  2. 2.Department of Computer Science and EngineeringFudan UniversityShanghaiChina

Personalised recommendations