Pose Invariant Face Recognition Technique Based on Eigen Space Approach Using Dual Registration Techniques After Masking

  • Tumpa Dey
  • Dibyendu GhoshalEmail author
Conference paper
Part of the Springer Proceedings in Physics book series (SPPHY, volume 194)


A novel method is proposed to solve different pose related problems related to face images in recognition system. The method removes the background of the image using masking. Subsequently, both training and testing images are registered by manual landmark detection and modeling the mapping process using affine transformation. The proposed method is found to solve the complications during scaling and rotation. Another registration method based on log-polar transformation is then proposed. Application of this method is found to improve arbitrary rotation angles and scale change. Lastly, log-polar images are projected into eigen space. These eigenface images are classified with the help of Euclidean distance. In the simulation based experimentation, IRIS face database is used. Recognition rate applying the proposed method is found to be 89.65%.


  1. 1.
    Nastar, C. and Mitschke, M., “Real time face recognition using feature combination,” Proc. 3rd IEEE International Conference on Automatic Face and Gesture Recognition. Nara, Japan, 312–317 (1998).Google Scholar
  2. 2.
    Brunelli, R. and Poggio, T., “Face Recognition: Features versus Templates,” IEEE Trans. Pattern Analysis and Machine Intelligence. 15(10), 1042–1052 (1993).Google Scholar
  3. 3.
    Chellappa, R., Wilson, C. L., and Sirohey, S., “Human and machine recognition of faces: A survey,” Proc. IEEE, 83, 705–740 (1995).Google Scholar
  4. 4.
    Hsieh, C.K. and Chen, Y.C., “Kernel-based pose invariant face recognition,” Proc. IEEE Int. Conf. Multimedia and Expo, 987–990 (2007).Google Scholar
  5. 5.
    Jafri, Rabia. and Arabnia, Hamid R., “A Survey of Face Recognition Techniques,” Journal of Information Processing Systems. 5 (2), 41–67 (2009).Google Scholar
  6. 6.
    Ding, X. Q., Fang, C., “Discussions on some problems in face recognition,” Proceedings. Advances in Biometric Person Authentication 3338, Lecture Notes Computer Science. Springer, 47–56 (2004).Google Scholar
  7. 7.
    Zitova, B. and Flusser, J., “Image registration methods: a survey,” Image Vis Compute, 21(11), 977–1000 (2003).Google Scholar
  8. 8.
    Allney, S., Morandi C., “Digital image registration using projections,” IEEE Trans. on Pattern Analysis and Machine Intelligence. PAMI-8, 222–233 (1986).Google Scholar
  9. 9.
    Lee, D. J., Kpile, T. F., Mitra, S., “Digital registration techniques for sequential fundus images,” International Society for Optics and Photonics, 293–300 (1988).Google Scholar
  10. 10.
    Fitzpatrick, J., Michael, D., Hill, L.G., Calvin, R. Maurer Jr., [Image registration], 447–513 (2000).Google Scholar
  11. 11.
    Tistarelli, M., Grosso, E., “Active vision-based face recognition: issues, applications and techniques in Face Recognition,” Springer. Berlin Heidelberg. 262–286 (1998).Google Scholar
  12. 12.
    Brown, L. G., “A survey of image registration techniques,” ACM Computing Surveys. 24(4), 325–376 (1992).Google Scholar
  13. 13.
    Zokai, S. and Wolberg, G. “Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations,” IEEE Trans Image Process, 14(10), 1422–1434 (2005).Google Scholar
  14. 14.
    Matungka, R., Zheng, Y.F., Ewing, R.L., “2D invariant object recognition using log-polar transform,” Proc. World Congress on Intelligent Control and Automation, 223–228 (2008).Google Scholar
  15. 15.
    Matungka, R., Zheng, Y.F., Ewing, R.L., “Image registration using adaptive polar transform,” IEEE Trans Image Process. 2009.Google Scholar
  16. 16.
    Turk, M. and Pentland, A., “Eigenfaces for recognition,” Journal of Cognitive Neuro-science. 3(1), 71–86 (1991).Google Scholar
  17. 17.
    Turk, M., Pentland, A., “Face recognition using eigenfaces,” Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 586–591 (1991).Google Scholar
  18. 18.
    Martínez, A. M., and Kak, A. C., “PCA versus LDA,” IEEE Trans. on Pattern Analysis and Machine Intelligence. 23(2), 228–233 (2001).Google Scholar
  19. 19.
    Serrano, S., “Eigenface Tutorial,” <>.

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.Department of ITWomen’s CollegeAgartalaIndia
  2. 2.Department of ECE and EIENIT AgartalaJirania, AgartalaIndia

Personalised recommendations