OSA's Digital Library

Applied Optics

Applied Optics

APPLICATIONS-CENTERED RESEARCH IN OPTICS

  • Vol. 34, Iss. 20 — Jul. 10, 1995
  • pp: 3950–3962

Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlators

Bahram Javidi, Jian Li, and Qing Tang  »View Author Affiliations


Applied Optics, Vol. 34, Issue 20, pp. 3950-3962 (1995)
http://dx.doi.org/10.1364/AO.34.003950


View Full Text Article

Enhanced HTML    Acrobat PDF (2065 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

We describe a nonlinear joint transform correlator-based two-layer neural network that uses a supervised learning algorithm for real-time face recognition. The system is trained with a sequence of facial images and is able to classify an input face image in real time. Computer simulations and optical experimental results are presented. The processor can be manufactured into a compact low-cost optoelectronic system. The use of the nonlinear joint transform correlator provides good noise robustness and good image discrimination.

© 1995 Optical Society of America

History
Original Manuscript: May 31, 1994
Revised Manuscript: November 2, 1994
Published: July 10, 1995

Citation
Bahram Javidi, Jian Li, and Qing Tang, "Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlators," Appl. Opt. 34, 3950-3962 (1995)
http://www.opticsinfobase.org/ao/abstract.cfm?URI=ao-34-20-3950

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you wish to use one of your free member downloads to view the figures, click "Enhanced HTML" above and access the figures from the article itself or from the navigation tab.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited