Face recognition system using accurate and rapid estimation of facial position and scale

  • Authors:

  • Takatsugu Hirayama;Yoshio Iwai;Masahiko Yachida

  • Affiliations:

  • Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan;Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan;Graduate School of Engineering Science, Osaka University, Toyonaka, Osaka, Japan

  • Venue:
  • AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Face recognition technology needs to be robust for arbitrary facial appearances. In this paper, we propose a face recognition system that is efficient and robust for facial scale variations. In the process of face recognition, facial position detection incurs the highest computational cost. To estimate both facial position and scale, there needs to be a trade-off between accuracy and efficiency. To resolve the trade-off, we propose a method that estimates facial position in parallel with facial scale. We apply the method to our proposed system and demonstrate the advantages of the proposed system through face recognition experiments. The proposed system is more efficient than any other system and can maintain high face recognition accuracy for facial scale variations.