3D face recognition using eigen-spectrum on the flattened facial surface

  • Authors:
  • Lei Zheng;Gang Pan;Zhaohui Wu

  • Affiliations:
  • Dept of Computer Science, Zhejiang University, Hangzhou, China;Dept of Computer Science, Zhejiang University, Hangzhou, China;Dept of Computer Science, Zhejiang University, Hangzhou, China

  • Venue:
  • SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel 3D face recognition approach The discrete facial surface firstly is mapped into an isomorphic 2D planar triangulation, attempting to preserve the intrinsic geometric properties Then power spectrum image of the flattened surface is employed for the followed eigenface, instead of the flattened surface image, in order to achieve the invariance in planar rotation Our method does not need 3D facial model registration during the whole recognition procedure The experiment using 3D_RMA demonstrates its comparable performance.