Facial expression recognition on multiple manifolds

  • Authors:

  • Rui Xiao;Qijun Zhao;David Zhang;Pengfei Shi

  • Affiliations:

  • Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China;Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR;Department of Computing, Hong Kong Polytechnic University, Hong Kong SAR and Shenzhen Graduate School, Harbin Institute of Technology, China;Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China

  • Venue:
  • Pattern Recognition
  • Year:
  • 2011

Quantified Score

Hi-index 0.01

Visualization

Abstract

Manifold learning has been successfully applied to facial expression recognition by modeling different expressions as a smooth manifold embedded in a high dimensional space. However, the assumption of single manifold is still arguable and therefore does not necessarily guarantee the best classification accuracy. In this paper, a generalized framework for modeling and recognizing facial expressions on multiple manifolds is presented which assumes that different expressions may reside on different manifolds of possibly different dimensionalities. The intrinsic features of each expression are firstly learned separately and the genetic algorithm (GA) is then employed to obtain the nearly optimal dimensionality of each expression manifold from the classification viewpoint. Classification is performed under a newly defined criterion that is based on the minimum reconstruction error on manifolds. Extensive experiments on both the Cohn-Kanade and Feedtum databases show the effectiveness of the proposed multiple manifold based approach.