New perspectives in face correlation: discrimination enhancement in face recognition based on iterative algorithm

Q. Wang; A. Alfalou; C. Brosseau

doi:10.1117/12.2228521

20 April 2016 New perspectives in face correlation: discrimination enhancement in face recognition based on iterative algorithm

Q. Wang, A. Alfalou, C. Brosseau

Author Affiliations +

Proceedings Volume 9845, Optical Pattern Recognition XXVII; 98450H (2016) https://doi.org/10.1117/12.2228521
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

Here, we report a brief review on the recent developments of correlation algorithms. Several implementation schemes and specific applications proposed in recent years are also given to illustrate powerful applications of these methods. Following a discussion and comparison of the implementation of these schemes, we believe that all-numerical implementation is the most practical choice for application of the correlation method because the advantages of optical processing cannot compensate the technical and/or financial cost needed for an optical implementation platform. We also present a simple iterative algorithm to optimize the training images of composite correlation filters. By making use of three or four iterations, the peak-to-correlation energy (PCE) value of correlation plane can be significantly enhanced. A simulation test using the Pointing Head Pose Image Database (PHPID) illustrates the effectiveness of this statement. Our method can be applied in many composite filters based on linear composition of training images as an optimization means.

Citation Download Citation

Q. Wang, A. Alfalou, and C. Brosseau "New perspectives in face correlation: discrimination enhancement in face recognition based on iterative algorithm", Proc. SPIE 9845, Optical Pattern Recognition XXVII, 98450H (20 April 2016); https://doi.org/10.1117/12.2228521

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available