Advertisement

An Example-Based Two-Step Face Hallucination Method through Coefficient Learning

  • Xiang Ma
  • Junping Zhang
  • Chun Qi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5627)

Abstract

Face hallucination is to reconstruct a high-resolution face image from a low-resolution one based on a set of high- and low-resolution training image pairs. This paper proposes an example-based two-step face hallucination method through coefficient learning. Firstly, the low-resolution input image and the low-resolution training images are interpolated to the same high-resolution space. Minimizing the square distance between the interpolated low-resolution input and the linear combination of the interpolated training images, the optimal coefficients of the interpolated training images are estimated. Then replacing the interpolated training images with the corresponding high-resolution training images in the linear combination formula, the result of first step is obtained. Furthermore, a local residue compensation scheme based on position is proposed to better recover high frequency information of face. Experiments demonstrate that our method can synthesize distinct high-resolution faces.

Keywords

Face hallucination Super-resolution Residue compensation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  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

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