Facial Expression Decomposition

  • Authors:
  • Hongcheng Wang;Narendra Ahuja

  • Affiliations:
  • -;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose a novel approach for facialexpression decomposition - Higher-Order Singular ValueDecomposition (HOSVD), a natural generalization ofmatrix SVD. We learn the expression subspace and personsubspace from a corpus of images showing seven basicfacial expressions, rather than resort to expert-coded facialexpression parameters as in [3]. We propose a simultaneousface and facial expression recognition algorithm,which can classify the given image into one of the sevenbasic facial expression categories, and then other facialexpressions of the new person can be synthesized using thelearned expression subspace model. The contributions ofthis work lie mainly in two aspects. First, we propose a newHOSVD based approach to model the mapping betweenpersons and expressions, used for facial expression synthesisfor a new person. Second, we realize simultaneous faceand facial expression recognition as a result of facialexpression decomposition. Experimental results are presentedthat illustrate the capability of the person subspaceand expression subspace in both synthesis and recognitiontasks. As a quantitative measure of the quality of synthesis,we propose using Gradient Minimum Square Error (GMSE)which measures the gradient difference between the originaland synthesized images.