Advertisement

Pattern Recognition and Image Analysis

, Volume 26, Issue 2, pp 379–384 | Cite as

On the false rejection ratio of face recognition based on automatic detected feature points

  • Kazuo OhzekiEmail author
  • Masahiro Takatsuka
  • Masaaki Kajihara
  • Yutaka Hirakawa
  • Kiyotsugu Sato
Applied Problems
  • 83 Downloads

Abstract

The authors propose a new face recognition system with an evaluation function using feature points. The feature points are detected automatically by Milborrow’s Stasm software. Before recognition, rotation compensation and size normalization are applied to the feature points. The main method is to calculate the squared error between the registered face and the input face as to length of a characteristic pair of feature points on face. The False Rejection Rate (FRR) for the registered and input face of the same person, and the False Acceptance Rate (FAR) for the registered face and a different person’s input face are evaluated. The input is a video sequence. Stable recognition is obtained with small FRR and FAR for the video of a period of 0.5 s.

Keywords

face recognition feature points normalization rotation compensation individual characteristics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    T. Jebara, Current Vision Systems for Face Recognition. http://www.cs.columbia.edu/~jebara/htmlpapers/UTHESIS/node8.html.Google Scholar
  2. 2.
    K. Bonnen, B. F. Klare, and A. K. Jain, “Componentbased representation in automated face recognition,” IEEE Trans. Inf. Forensics Security 8 1, 239–253 (2013).CrossRefGoogle Scholar
  3. 3.
    Facial Feature Detection and Tracking. http:// wwwluxandcom/facesdk/#facialfeatures.Google Scholar
  4. 4.
    S. Milborrow and F. Nicolls, “Locating facial features with an extended active shape model,” in Proc. 10th European Conf. on Computer Vision (ECCV’08) (Springer, Berlin, 2008), Part IV, pp. 504–513.Google Scholar
  5. 5.
    F. Milborrow and F. Nicolls, “Active shape models with SIFT descriptors and MARS,” in Proc Int. Conf. on Computer Vision Theory and Applications (VISAPP) (Lisbon, 2014), pp. 380–387.Google Scholar
  6. 6.
    S. Milborrow, Active Shape Models with SIFT Descriptors and MAR S. http://wwwmilbouserssonicnet/stasm.Google Scholar
  7. 7.
    Zhe Sun, Baopu Li, Ran Zhou, Huimin Zheng., and M. Q.-H. Meng, “Removal of non-informative frames for wireless capsule endoscopy video segmentation,” in Proc. IEEE Int. Conf. on Automation and Logistics (ICAL) (Zhengzhou, Aug. 2012), pp. 294–299.Google Scholar
  8. 8.
    Kazuo Ohzeki, YuanYu Wei, Yutaka Hirakawa, and Toru Sugimoto, “Authentication system using encrypted discrete biometrics data,” in Proc. TRUST 2014 (Heraclion, June 30–July 2, 2014), pp. 210–211.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2016

Authors and Affiliations

  • Kazuo Ohzeki
    • 1
    Email author
  • Masahiro Takatsuka
    • 1
  • Masaaki Kajihara
    • 1
  • Yutaka Hirakawa
    • 1
  • Kiyotsugu Sato
    • 2
  1. 1.Graduate School of Engineering and Science Shibaura-Institute of Technology 3-7-5 ToyosuKoutou-ku, TokyoJapan
  2. 2.Dept. of Information Processing Engineering College of Industrial Technology 1-27-1 NishikoyaAmagasaki, HyogoJapan

Personalised recommendations