20 April 2016 New perspectives in face correlation: discrimination enhancement in face recognition based on iterative algorithm
Author Affiliations +
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.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Q. Wang, Q. Wang, A. Alfalou, A. Alfalou, C. Brosseau, 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); doi: 10.1117/12.2228521; https://doi.org/10.1117/12.2228521
PROCEEDINGS
11 PAGES


SHARE
Back to Top