Abstract
The authors previously constructed a highly accurate fast face recognition optical correlator (FARCO) [E. Watanabe and K. Kodate: Opt. Rev. 12 (2005) 460], and subsequently developed an improved, super high-speed FARCO (S-FARCO), which is able to process several hundred thousand frames per second. The principal advantage of our new system is its wide applicability to any correlation scheme. Three different configurations were proposed, each depending on correlation speed. This paper describes and evaluates a software correlation filter. The face recognition function proved highly accurate, seeing that a low-resolution facial image size (64 × 64 pixels) has been successfully implemented. An operation speed of less than 10 ms was achieved using a personal computer with a central processing unit (CPU) of 3 GHz and 2 GB memory. When we applied the software correlation filter to a high-security cellular phone face recognition system, experiments on 30 female students over a period of three months yielded low error rates: 0% false acceptance rate and 2% false rejection rate. Therefore, the filtering correlation works effectively when applied to low resolution images such as web-based images or faces captured by a monitoring camera.
Similar content being viewed by others
References
M. Kaneko O. Hasegawa (1999) IEICE Trans. Inf. Syst. E82-D 589
T. Kanade (1971) Dr. Engineering, Faculty of Engineering Kyoto University Kyoto
L. Sirovich M. Kirby (1991) J. Opt. Soc. Am. 4 519
M. Savvides, B. V. K. Vijaya Kumar, and P. K. Khosla: Proc. 17th Int. Conf. Pattern Recognition (ICPR'04), Cambridge, 2004, Vol. 3, p. 810.
J. Goodman M. Moeller (2004) Chap. 8 Introduction to Fourier Optics, Vol. 1 Roberts & Company Publishers Colorado 237
R. Thapliya T. Kamiya (2000) Appl. Opt. 39 5309 Occurrence Handle2000ApOpt..39.5309T Occurrence Handle10.1364/AO.39.005309
R. Inaba E. Watanabe K. Kodate (2003) Opt. Rev. 10 255 Occurrence Handle10.1007/s10043-003-0255-9
K. Kodate R. Inaba E. Watanabe T. Kamiya (2002) Meas. Sci. Technol. 13 1756 Occurrence Handle10.1088/0957-0233/13/11/312 Occurrence Handle2002MeScT..13.1756K
Y. Kobayashi Y. Toyoda (1999) Opt. Eng. 38 1205 Occurrence Handle10.1117/1.602269 Occurrence Handle1999OptEn..38.1205K
D. T. Carrott G. Mallaley R. B. Dydyk S. A. Mills (1998) Proc. SPIE 3386 38 Occurrence Handle10.1117/12.304786 Occurrence Handle1998SPIE.3386...38C
E. Watanabe K. Kodate (2005) Appl. Opt. 44 666 Occurrence Handle10.1364/AO.44.000666 Occurrence Handle2005ApOpt..44..666W
E. Watanabe K. Kodate (2005) Opt. Rev. 12 460 Occurrence Handle10.1007/s10043-005-0460-9
E. Watanabe K. Kodate (2006) Jpn. J. Appl. Phys. 45 6759 Occurrence Handle10.1143/JJAP.45.6759 Occurrence Handle2006JaJAP..45.6759W
E. Watanabe K. Kodate (2006) Proc. SPIE 6245 147
H. Horimai X. Tan (2006) Appl. Opt. 45 910 Occurrence Handle10.1364/AO.45.000910 Occurrence Handle2006ApOpt..45..910H
A. J. Mansfield J. L. Wayman (2002) Biometric Testing Best Practices National Physical Laboratory Teddington
J. L. Horner P. D. Gianino (1984) Appl. Opt. 23 812 Occurrence Handle1984ApOpt..23..812H Occurrence Handle10.1364/AO.23.000812
F. Tarres and A. Rama: GTAV Face Database available at; http://gps-tsc.upc.es/GTAV/ResearchAreas/UPCFaceDatabase/GTAVFaceDatabase.html.
E. Watanabe S. Ishikawa M. Ohta K. Kodate (2007) IEEJ Trans. Electron. Inform. Syst. 127 636 Occurrence Handle10.1541/ieejeiss.127.636
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Watanabe, E., Ishikawa, S. & Kodate, K. A Highly Accurate Face Recognition System Using Filtering Correlation. OPT REV 14, 255–259 (2007). https://doi.org/10.1007/s10043-007-0255-2
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10043-007-0255-2