Implementation of a high-speed face recognition system that uses an optical parallel correlator.

We implement a fully automatic fast face recognition system by using a 1000 frame/s optical parallel correlator designed and assembled by us. The operational speed for the 1:N (i.e., matching one image against N, where N refers to the number of images in the database) identification experiment (4000 face images) amounts to less than 1.5 s, including the preprocessing and postprocessing times. The binary real-only matched filter is devised for the sake of face recognition, and the system is optimized by the false-rejection rate (FRR) and the false-acceptance rate (FAR), according to 300 samples selected by the biometrics guideline. From trial 1:N identification experiments with the optical parallel correlator, we acquired low error rates of 2.6% FRR and 1.3% FAR. Facial images of people wearing thin glasses or heavy makeup that rendered identification difficult were identified with this system.

[1]  D A Gregory,et al.  Rotation invariant pattern recognition with a programmable joint transform correlator. , 1989, Applied optics.

[2]  K. Kodate,et al.  Binary zone-plate array for a parallel joint transform correlator applied to face recognition. , 1999, Applied optics.

[3]  Kashiko Kodate,et al.  Facial Recognition System with Compact Optical Parallel Correlator Using Vertical-Cavity Surface-Emitting Laser Array Module , 2004 .

[4]  R Thapliya,et al.  Optimization of multichannel parallel joint transform correlator for accelerated pattern recognition. , 2000, Applied optics.

[5]  Haruyoshi Toyoda,et al.  Development of an optical joint transform correlation system for fingerprint recognition , 1999 .

[6]  F T Yu,et al.  Design of a bipolar composite filter by a simulated annealing algorithm. , 1995, Optics letters.

[7]  Eriko Watanabe,et al.  Security Applications of Optical Face Recognition System: Access Control in E-Learning , 2003 .

[8]  R. Juday,et al.  Design of phase-only, binary phase-only, and complex ternary matched filters with increased signal-to-noise ratios for colored noise. , 1991, Optics letters.

[9]  Douglas L. Jones,et al.  Real-valued fast Fourier transform algorithms , 1987, IEEE Trans. Acoust. Speech Signal Process..

[10]  Alain Bergeron,et al.  Optical correlator for industrial applications, quality control and target tracking , 2000 .

[11]  J. Goodman,et al.  A technique for optically convolving two functions. , 1966, Applied optics.

[12]  Eriko Watanabe,et al.  Facial recognition by a compact parallel optical correlator , 2002 .

[13]  Gregory O. Gheen.  Design considerations for low-clutter, distortion invariant correlation filters , 1990 .

[14]  K Kodate,et al.  Optimization and application of hybrid-level binary zone plates. , 2001, Applied optics.