Chinese Journal of Lasers, Volume. 39, Issue s2, 209004(2012)

Large-Scale Face Recognition Using Optic-Electronic Hybrid Joint Transform Correlator

Guo Suoli1、*, Cheng Panpan1, Liu Yanfei1, and Jia Hui2
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • show less

    A new method for large-scale face recognition is proposed. In order to realize 1N identification, optical joint transform correlator is used to complete related calculation which consuming the largest time in image recognition, and electrical method is used to subtract power spectrum. By combining the computer pattern′s high accuracy with the optical pattern′s high speed, the recognition′s speed and accuracy are improved. An evaluation criteria is also established to evaluate the recognition performance of this method. The computer simulation results show that the method can eliminate the central zero-order diffraction and sharp auto-correlation peak. When the recognition threshold value is in [0.61,0.62], both false match rate and false non-match rate are 0.

    Tools

    Get Citation

    Copy Citation Text

    Guo Suoli, Cheng Panpan, Liu Yanfei, Jia Hui. Large-Scale Face Recognition Using Optic-Electronic Hybrid Joint Transform Correlator[J]. Chinese Journal of Lasers, 2012, 39(s2): 209004

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: holography and information processing

    Received: May. 28, 2012

    Accepted: --

    Published Online: Dec. 24, 2012

    The Author Email: Suoli Guo (chengpan432500@163.com)

    DOI:10.3788/cjl201239.s209004

    Topics