Abstract

Using biometrics for subject verification can significantly improve security over that of approaches based on passwords and personal identification numbers, both of which people tend to lose or forget. In biometric verification the system tries to match an input biometric (such as a fingerprint, face image, or iris image) to a stored biometric template. Thus correlation filter techniques are attractive candidates for the matching precision needed in biometric verification. In particular, advanced correlation filters, such as synthetic discriminant function filters, can offer very good matching performance in the presence of variability in these biometric images (e.g., facial expressions, illumination changes, etc.). We investigate the performance of advanced correlation filters for face, fingerprint, and iris biometric verification.

© 2004 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. P. J. Philips, P. Grother, R. Micheals, D. M. Blackburn, E. Tabassi, M. Bone, “Face recognition vendor test 2002: overview and summary,” http://www.frvt2002.org .
  2. B. V. K. Vijaya Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
    [CrossRef]
  3. D. O. North, “An analysis of the factors which determine signal/noise discriminations in pulsed carrier systems,” Proc. IEEE 51, 1016–1027 (1963).
    [CrossRef]
  4. A. VanderLugt, “Signal detection by complex spatial filtering,” IEEE Trans. Inf. Th. 10, 139–145 (1964).
    [CrossRef]
  5. C. F. Hester, D. Casasent, “Multivariant technique for multiclass pattern recognition,” Appl. Opt. 19, 1758–1761 (1980).
    [CrossRef] [PubMed]
  6. B. V. K. Vijaya Kumar, “Minimum variance synthetic discriminant functions,” J. Opt. Soc. Am. A 3, 1579–1584 (1986).
    [CrossRef]
  7. A. Mahalanobis, B. V. K. Vijaya Kumar, D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3630 (1987).
    [CrossRef] [PubMed]
  8. P. Réfrégier, “Optimal trade-off filters for noise robustness, sharpness of the correlation peak, and Horner efficiency,” Opt. Lett. 16, 829–831 (1991).
    [CrossRef] [PubMed]
  9. A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, J. F. Epperson, “Unconstrained correlation filters,” Appl. Opt. 33, 3751–3759 (1994).
    [CrossRef] [PubMed]
  10. A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, “Distance classifier correlation filters for distortion tolerance, discrimination and clutter rejection,” in Photonics for Processors, Neural Networks, and Memories, J. L. Horner, B. Javidi, S. T. Kowel, W. J. Miceli, eds., Proc. SPIE2026, 325–335 (1993).
    [CrossRef]
  11. B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
    [CrossRef]
  12. A. Mahalanobis, B. V. K. Vijaya Kumar, “Polynomial filters for higher-order and multi-input information fusion,” in Proceedings of the Eleventh Euro-American Optoelectronic Workshop, Spain, June1997, pp. 221–231.
  13. A. V. Oppenheim, R. W. Schaffer, Digital Signal Processing (Prentice-Hall, Englewood Cliffs, N.J., 1975).
  14. Advanced Multimedia Processing Laboratory web page, Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pa. (November2003), http://amp.ece.cmu.edu .
  15. F. J. Huang, T. Chen, “Tracking of multiple faces for human-computer interfaces and virtual environments,” IEEE International Conference on Multimedia and Expo, (Institute of Electrical and Electronics Engineers, New York, 2000), pp. 1563–1566.
  16. M. Turk, A. Pentland, “Eigenfaces for recognition,” J. Cogn. Neurosci. 3, 71–86 (1991).
    [CrossRef]
  17. X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
    [CrossRef]
  18. T. Sim, S. Baker, M. Bsat, “The CMU pose, illumination, and expression (PIE) database of human faces,” Technical Report CMU-RI-TR-01-02 (Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa., 2001).
  19. P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
    [CrossRef]
  20. A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
    [CrossRef]
  21. A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
    [CrossRef]
  22. C. I. Watson, NIST Special Database 24—Live-Scan Digital Video Fingerprint Database, 1998, http://www.nist.gov/srd/nists24.htm .
  23. J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. 15, 1148–1161 (1993).
    [CrossRef]
  24. Miles Research Laboratory, http://www.milesresearch.com .

2003

X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
[CrossRef]

2000

B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
[CrossRef]

1997

P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
[CrossRef]

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

1994

1993

J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. 15, 1148–1161 (1993).
[CrossRef]

1992

1991

1987

1986

1980

1964

A. VanderLugt, “Signal detection by complex spatial filtering,” IEEE Trans. Inf. Th. 10, 139–145 (1964).
[CrossRef]

1963

D. O. North, “An analysis of the factors which determine signal/noise discriminations in pulsed carrier systems,” Proc. IEEE 51, 1016–1027 (1963).
[CrossRef]

Baker, S.

T. Sim, S. Baker, M. Bsat, “The CMU pose, illumination, and expression (PIE) database of human faces,” Technical Report CMU-RI-TR-01-02 (Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa., 2001).

Belhumeur, P.

P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Bolle, R.

A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
[CrossRef]

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

Bsat, M.

T. Sim, S. Baker, M. Bsat, “The CMU pose, illumination, and expression (PIE) database of human faces,” Technical Report CMU-RI-TR-01-02 (Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa., 2001).

Casasent, D.

Chen, T.

X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
[CrossRef]

F. J. Huang, T. Chen, “Tracking of multiple faces for human-computer interfaces and virtual environments,” IEEE International Conference on Multimedia and Expo, (Institute of Electrical and Electronics Engineers, New York, 2000), pp. 1563–1566.

Daugman, J. G.

J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. 15, 1148–1161 (1993).
[CrossRef]

Epperson, J. F.

Hespanha, J.

P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Hester, C. F.

Hong, L.

A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
[CrossRef]

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

Huang, F. J.

F. J. Huang, T. Chen, “Tracking of multiple faces for human-computer interfaces and virtual environments,” IEEE International Conference on Multimedia and Expo, (Institute of Electrical and Electronics Engineers, New York, 2000), pp. 1563–1566.

Jain, A.

A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
[CrossRef]

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

Kriegman, D.

P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Liu, X.

X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
[CrossRef]

Mahalanobis, A.

B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
[CrossRef]

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, J. F. Epperson, “Unconstrained correlation filters,” Appl. Opt. 33, 3751–3759 (1994).
[CrossRef] [PubMed]

A. Mahalanobis, B. V. K. Vijaya Kumar, D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3630 (1987).
[CrossRef] [PubMed]

A. Mahalanobis, B. V. K. Vijaya Kumar, “Polynomial filters for higher-order and multi-input information fusion,” in Proceedings of the Eleventh Euro-American Optoelectronic Workshop, Spain, June1997, pp. 221–231.

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, “Distance classifier correlation filters for distortion tolerance, discrimination and clutter rejection,” in Photonics for Processors, Neural Networks, and Memories, J. L. Horner, B. Javidi, S. T. Kowel, W. J. Miceli, eds., Proc. SPIE2026, 325–335 (1993).
[CrossRef]

North, D. O.

D. O. North, “An analysis of the factors which determine signal/noise discriminations in pulsed carrier systems,” Proc. IEEE 51, 1016–1027 (1963).
[CrossRef]

Oppenheim, A. V.

A. V. Oppenheim, R. W. Schaffer, Digital Signal Processing (Prentice-Hall, Englewood Cliffs, N.J., 1975).

Pankati, S.

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

Pentland, A.

M. Turk, A. Pentland, “Eigenfaces for recognition,” J. Cogn. Neurosci. 3, 71–86 (1991).
[CrossRef]

Réfrégier, P.

Schaffer, R. W.

A. V. Oppenheim, R. W. Schaffer, Digital Signal Processing (Prentice-Hall, Englewood Cliffs, N.J., 1975).

Sim, T.

T. Sim, S. Baker, M. Bsat, “The CMU pose, illumination, and expression (PIE) database of human faces,” Technical Report CMU-RI-TR-01-02 (Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa., 2001).

Sims, S. R. F.

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, J. F. Epperson, “Unconstrained correlation filters,” Appl. Opt. 33, 3751–3759 (1994).
[CrossRef] [PubMed]

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, “Distance classifier correlation filters for distortion tolerance, discrimination and clutter rejection,” in Photonics for Processors, Neural Networks, and Memories, J. L. Horner, B. Javidi, S. T. Kowel, W. J. Miceli, eds., Proc. SPIE2026, 325–335 (1993).
[CrossRef]

Takessian, A.

B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
[CrossRef]

Turk, M.

M. Turk, A. Pentland, “Eigenfaces for recognition,” J. Cogn. Neurosci. 3, 71–86 (1991).
[CrossRef]

VanderLugt, A.

A. VanderLugt, “Signal detection by complex spatial filtering,” IEEE Trans. Inf. Th. 10, 139–145 (1964).
[CrossRef]

Vijaya Kumar, B. V. K.

X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
[CrossRef]

B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
[CrossRef]

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, J. F. Epperson, “Unconstrained correlation filters,” Appl. Opt. 33, 3751–3759 (1994).
[CrossRef] [PubMed]

B. V. K. Vijaya Kumar, “Tutorial survey of composite filter designs for optical correlators,” Appl. Opt. 31, 4773–4801 (1992).
[CrossRef]

A. Mahalanobis, B. V. K. Vijaya Kumar, D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3630 (1987).
[CrossRef] [PubMed]

B. V. K. Vijaya Kumar, “Minimum variance synthetic discriminant functions,” J. Opt. Soc. Am. A 3, 1579–1584 (1986).
[CrossRef]

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, “Distance classifier correlation filters for distortion tolerance, discrimination and clutter rejection,” in Photonics for Processors, Neural Networks, and Memories, J. L. Horner, B. Javidi, S. T. Kowel, W. J. Miceli, eds., Proc. SPIE2026, 325–335 (1993).
[CrossRef]

A. Mahalanobis, B. V. K. Vijaya Kumar, “Polynomial filters for higher-order and multi-input information fusion,” in Proceedings of the Eleventh Euro-American Optoelectronic Workshop, Spain, June1997, pp. 221–231.

Appl. Opt.

IEEE Trans. Image Process.

B. V. K. Vijaya Kumar, A. Mahalanobis, A. Takessian, “Optimal tradeoff circular harmonic function correlation filter methods providing controlled in-plane rotation response,” IEEE Trans. Image Process. 9, 1025–1034 (2000).
[CrossRef]

IEEE Trans. Inf. Th.

A. VanderLugt, “Signal detection by complex spatial filtering,” IEEE Trans. Inf. Th. 10, 139–145 (1964).
[CrossRef]

IEEE Trans. Pattern Anal. Mach.

J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. 15, 1148–1161 (1993).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell.

P. Belhumeur, J. Hespanha, D. Kriegman, “Eigenfaces vs fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

A. Jain, L. Hong, R. Bolle, “On-line fingerprint verification,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 302–314 (1997).
[CrossRef]

J. Cogn. Neurosci.

M. Turk, A. Pentland, “Eigenfaces for recognition,” J. Cogn. Neurosci. 3, 71–86 (1991).
[CrossRef]

J. Opt. Soc. Am. A

Opt. Lett.

Pattern Recogn.

X. Liu, T. Chen, B. V. K. Vijaya Kumar, “Face authentication for multiple subjects using eigenflow,” Pattern Recogn. 36, 313–328 (2003).
[CrossRef]

Proc. IEEE

D. O. North, “An analysis of the factors which determine signal/noise discriminations in pulsed carrier systems,” Proc. IEEE 51, 1016–1027 (1963).
[CrossRef]

A. Jain, L. Hong, S. Pankati, R. Bolle, “An identity-authentication system using fingerprints,” Proc. IEEE 85, 1365–1388 (1997).
[CrossRef]

Other

C. I. Watson, NIST Special Database 24—Live-Scan Digital Video Fingerprint Database, 1998, http://www.nist.gov/srd/nists24.htm .

A. Mahalanobis, B. V. K. Vijaya Kumar, “Polynomial filters for higher-order and multi-input information fusion,” in Proceedings of the Eleventh Euro-American Optoelectronic Workshop, Spain, June1997, pp. 221–231.

A. V. Oppenheim, R. W. Schaffer, Digital Signal Processing (Prentice-Hall, Englewood Cliffs, N.J., 1975).

Advanced Multimedia Processing Laboratory web page, Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, Pa. (November2003), http://amp.ece.cmu.edu .

F. J. Huang, T. Chen, “Tracking of multiple faces for human-computer interfaces and virtual environments,” IEEE International Conference on Multimedia and Expo, (Institute of Electrical and Electronics Engineers, New York, 2000), pp. 1563–1566.

A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, “Distance classifier correlation filters for distortion tolerance, discrimination and clutter rejection,” in Photonics for Processors, Neural Networks, and Memories, J. L. Horner, B. Javidi, S. T. Kowel, W. J. Miceli, eds., Proc. SPIE2026, 325–335 (1993).
[CrossRef]

T. Sim, S. Baker, M. Bsat, “The CMU pose, illumination, and expression (PIE) database of human faces,” Technical Report CMU-RI-TR-01-02 (Robotics Institute, Carnegie Mellon University, Pittsburgh, Pa., 2001).

Miles Research Laboratory, http://www.milesresearch.com .

P. J. Philips, P. Grother, R. Micheals, D. M. Blackburn, E. Tabassi, M. Bone, “Face recognition vendor test 2002: overview and summary,” http://www.frvt2002.org .

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (11)

Fig. 1
Fig. 1

Block diagram of the correlation process. FFT, fast Fourier transform; IFFT, inverse fast Fourier transform.

Fig. 2
Fig. 2

Schematic of the DCCF transformation process, which increases the interclass distance and makes the classes more compact.

Fig. 3
Fig. 3

The PCF architecture shown to the Nth order, with h 1h N representing the filters.

Fig. 4
Fig. 4

Estimation of the PSR.

Fig. 5
Fig. 5

Example images from the Advanced Multimedia Processing Laboratory’s facial expression database.

Fig. 6
Fig. 6

PSRs for person 1 (top), and person 2 (bottom). Solid curves, authentic subjects; dotted curves, imposters; “x” symbols, training images.

Fig. 7
Fig. 7

Twenty-one images from the PIE database for person 2. Each of these images was captured under different illumination conditions and without background lighting.

Fig. 8
Fig. 8

PSR comparison between MACE and unconstrained MACE (UMACE) filters by use of the PIE-L dataset (with background lighting) for person 2. Authentic subjects, top plot; imposters, bottom plot.

Fig. 9
Fig. 9

Example images from the thumbprint of person 10.

Fig. 10
Fig. 10

ROC curve for 10 fingerprint classes (see legend), with 20 training images used per class.

Fig. 11
Fig. 11

Sixteen synthesized iris images for class 1: (from left to right) one original, four Gaussian noised, four rotated, four with illumination angles changed, and three randomly occluded.

Tables (3)

Tables Icon

Table 1 Error Percentages for all 13 MACE Filters Synthesized with 3 Training Images

Tables Icon

Table 2 Error Percentages for all 13 Individual Subspaces with 3 Training Images Per Person

Tables Icon

Table 3 EERs for Various Distortion Sets for Each Filter Type

Equations (27)

Equations on this page are rendered with MathJax. Learn more.

X+h=u,
h=XX+X-1u.
h=D-1XX+D-1X-1u.
h=C-1XX+C-1X-1u.
h=T-1XX+T-1X-1u,
Fr, θ=k=- Fkrexpjkθ,
Fkr=12π02π Fr, θexp-jkθdθ.
Cτθ=r=0θ=02πk=- Fkrexpjkθ+τθ×l=- Hl*rexp-jlθrdrdθ =r=0k=-l=- FkrHl*rexpjkτθ×θ=02πexpjk-lθdθrdr=2π r=0k=- FkrHk*rexpjkτθrdr=k=- Ck expjkτθ,
Ck=2π r=0 FkrHk*rrdr.
Cτθ=k=- Ck expjkτθ.
ASM=1Ni=1Nmngim, n-g¯m, n2,
g¯m, n=1Nj=1N gjm, n
ASM=1Ndi=1N |Xi*h-M*h|2=1Ndi=1Nh+Xi-MXi-M*h=h+1Ndi=1NXi-MXi-M*h=h+Sh,
S=1Ndi=1NXi-MXi-M*
ACH=1Ni=1Nx+h=m+h.
Jh=|ACH|2ASM+ONV=|m+h|2h+Sh+h+Ch=h+mm+hh+S+Ch.
h=γS+C-1m,
dk=|Hx-Hmk|2=x-mk+H+Hx-mk.
Ah=1C2k=1Cl=1C |v¯kl|2=1C2k=1Cl=1C |mk+h-ml+h|2=1C2k=1Cl=1Ch+ml-mkml-mk+h=h+1Ck=1cm-mkm-mk+h=h+Th,
T=1Ck=1Cm-mkm-mk+
Bh=1Ck=1C1Ni=1Nh+Xik-MkXik-Mk*h=h+Sh.
Jh=AhBh=h+Thh+Sh
dk=|H*z-H*mk|2=p+bk-z+hk+hk+z,1kC,
gx=A1x1+A2x2++ANxN,
Aixihim, n  xim, n,
gxm, n=i=1N him, n  xim, n.
PSR=peak-meanσ.

Metrics