Robust 3d face recognition based on rejection and adaptive region selection

  • Authors:
  • Xiaoli Li;Feipeng Da

  • Affiliations:
  • Key Laboratory of Measurement and Control for, Complex System of Ministry of Education, Research Institute of Automation, Southeast University, Nanjing, China;Key Laboratory of Measurement and Control for, Complex System of Ministry of Education, Research Institute of Automation, Southeast University, Nanjing, China

  • Venue:
  • ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an efficient 3D face recognition algorithm and demonstrate its performance on the FRGC v2.0 data set The pose of a 3D face is automatically corrected based on the nose tip and principle component analysis(PCA) The facial curve in the nose region is used to eliminate a large number of dissimilar faces in the gallery at an early stage Facial curves in the regions of forehead and cheeks are used to produce a mapping of facial deformation caused by expressions The remaining faces after rejection are then verified using a region-based matching approach This approach adaptively selects regions which are relatively steady based on the deformation mapping, and matches them separately At last, the results are fused using the sum rule Promising experimental results are achieved on FRGC v2.0 data set.