Automatic facial pose determination of 3D range data for face model and expression identification

  • Authors:
  • Xiaozhou Wei;Peter Longo;Lijun Yin

  • Affiliations:
  • Department of Computer Science, State University of New York at Binghamton, Binghamton, NY;Department of Computer Science, State University of New York at Binghamton, Binghamton, NY;Department of Computer Science, State University of New York at Binghamton, Binghamton, NY

  • Venue:
  • ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Many of the contemporary 3D facial recognition and facial expression recognition algorithms depend on locating primary facial features, such as the eyes, nose, or lips. Others are dependent on determining the pose of the face. We propose a novel method for limiting the search space needed to find these "interesting features." We then show that our algorithm can be used in conjunction with surface labeling to robustly determine the pose of a face. Our approach does not require any type of training. It is pose-invariant and can be applied to both manually cropped models and raw range data, which can include the neck, ears, shoulders, and other noise. We applied the proposed algorithm to our created 3D range model database, the experiments show the promising results to classify individual faces and individual facial expressions.