Efficient Image Plane Rotation Invariant Frequency Domain Face Recognition Technique Using Eye Localization

  • Papia Banerjee
  • Pradipta K. Banerjee
  • Asit K. Datta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)

Abstract

An efficient frequency domain face recognition under arbitrary image plane rotations by single correlation filtering approach is proposed where faces are registered with eye detection. Here eye detection problem is carried out using shift invariant property of correlation filter. The proposed eye detection method includes log-polar transformation, correlation and regression neural network estimation. Proposed system shows the recognition improvement comparing to straightforward correlation filtering and multi-correlation approach.

Keywords

Face Image Angular Position Generalize Regression Neural Network Generalize Regression Neural Network Model Correlation Plane 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Mahalanobis, A., Kumar, B.V., Song, S., Sims, S., Epperson, J.: Unconstrained correlation filter. Applied Optics 33, 3751–3759 (1994)CrossRefGoogle Scholar
  2. 2.
    Banerjee, P.K., Datta, A.K.: Generalized regression neural network trained preprocessing of frequency domain correlation filter for improved face recognition and its optical implementation. Optics and Laser Technology 45, 217–227 (2013)CrossRefGoogle Scholar
  3. 3.
    Bone, P., Young, R., Chatwin, C.: Position-, rotation-, scale-, and orientation-invariant multiple object recognition from cluttered scenes. Optical Engineering 45 (2006)Google Scholar
  4. 4.
    Kumar, B.V.K., Savvides, M., Xie, C., Venkataramani, K., Thornton, J., Mahalanobis, A.: Biometric verification with correlation filters. Applied Optics 43(2), 391–402 (2004)CrossRefGoogle Scholar
  5. 5.
    Rutkowski, L.: Generalized regression neural networks in time-varying environment. IEEE Transaction on Neural Networks 15(3), 576–596 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Papia Banerjee
    • 1
  • Pradipta K. Banerjee
    • 2
  • Asit K. Datta
    • 3
  1. 1.Department of Computer Science and EngineeringABACUS Inst. of Engg. & Mgmt.HooglyIndia
  2. 2.Department of Electrical EngineeringFuture Institute of Engineering and ManagementKolkataIndia
  3. 3.Department of Applied Optics and PhotonicsUniversity of CalcuttaKolkataIndia

Personalised recommendations