Abstract

An important step in the fingerprint identification system is the reliable extraction of distinct features from fingerprint images. Identification performance is directly related to the enhancement of fingerprint images during or after the enrollment phase. Among the various enhancement algorithms, artificial-intelligence-based feature-extraction techniques are attractive owing to their adaptive learning properties. We present a new supervised filtering technique that is based on a dynamic neural-network approach to develop a robust fingerprint enhancement algorithm. For pattern matching, a joint transform correlation (JTC) algorithm has been incorporated that offers high processing speed for real-time applications. Because the fringe-adjusted JTC algorithm has been found to yield a significantly better correlation output compared with alternate JTCs, we used this algorithm for the identification process. Test results are presented to verify the effectiveness of the proposed algorithm.

© 2005 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
    [CrossRef]
  2. E. Saatci, V. Tavsanoglu, “Fingerprint image enhancement using CNN Gabor-type filters,” in Proceedings of the Seventh IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA ’02) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 2002), pp. 377–382.
    [CrossRef]
  3. O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).
  4. A. Bal, M. S. Alam, “Feature extraction technique based on Hopfield neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 343–348 (2004).
    [CrossRef]
  5. M. S. Alam, M. A. Karim, “Fringe-adjusted joint transform correlation,” Appl. Opt. 32, 4344–4350 (1993).
    [CrossRef] [PubMed]
  6. T. M. Hagan, H. B. Demuth, M. Beale, Neural Networks Design (PWS-Kent, Boston, Mass., 1995).
  7. F. Cheng, F. T. S. Yu, D. A. Gregory, “Multitarget detection using spatial synthesis joint transform correlator,” Appl. Opt. 32, 6521–6526 (1993).
    [CrossRef] [PubMed]
  8. Q. Tang, B. Javidi, “Multiple-object detection with a chirp-encoded joint transform correlator,” Appl. Opt. 32, 4344–4350 (1993).
    [CrossRef]
  9. P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
    [CrossRef]
  10. B. Javidi, C. Kuo, “Joint transform image correlation using a binary spatial light modulator at the Fourier plane,” Appl. Opt. 27, 663–665 (1988).
    [CrossRef] [PubMed]
  11. S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).
  12. M. S. Alam, “Deblurring using fringe-adjusted joint transform correlation,” Opt. Eng. 37, 556–564 (1998).
    [CrossRef]
  13. M. S. Alam, M. A. Karim, “Improved correlation discrimination in a multiobject bipolar joint transform correlator,” Opt. Laser Technol. 24, 45–50 (1992).
    [CrossRef]
  14. F. T. S. Yu, F. Cheng, T. Nagata, D. A. Gregory, “Effects of fringe binarization of multi-object joint transform correlation,” Appl. Opt. 28, 2988–2990 (1989).
    [CrossRef] [PubMed]
  15. A. Bal, M. S. Alam, A. El-Saba, “Optical fingerprint identification using cellular neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 349–355 (2004).
    [CrossRef]
  16. B. V. K. V. Kumar, L. Hassebrook, “Performance measures for correlation filters,” Appl. Opt. 29, 2997–3001 (1990).
    [CrossRef] [PubMed]
  17. R. Singh, B. V. K. V. Kumar, “Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification,” in Algorithms for Synthetic Aperture Radar Imagery IX, E. G. Zelnio, ed., Proc. SPIE4727, 265–276 (2002).
    [CrossRef]
  18. A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
    [CrossRef]

2003 (1)

A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
[CrossRef]

2002 (1)

O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).

1999 (1)

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

1998 (1)

M. S. Alam, “Deblurring using fringe-adjusted joint transform correlation,” Opt. Eng. 37, 556–564 (1998).
[CrossRef]

1993 (3)

1992 (1)

M. S. Alam, M. A. Karim, “Improved correlation discrimination in a multiobject bipolar joint transform correlator,” Opt. Laser Technol. 24, 45–50 (1992).
[CrossRef]

1990 (2)

S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).

B. V. K. V. Kumar, L. Hassebrook, “Performance measures for correlation filters,” Appl. Opt. 29, 2997–3001 (1990).
[CrossRef] [PubMed]

1989 (1)

1988 (1)

Alam, M. S.

M. S. Alam, “Deblurring using fringe-adjusted joint transform correlation,” Opt. Eng. 37, 556–564 (1998).
[CrossRef]

M. S. Alam, M. A. Karim, “Fringe-adjusted joint transform correlation,” Appl. Opt. 32, 4344–4350 (1993).
[CrossRef] [PubMed]

M. S. Alam, M. A. Karim, “Improved correlation discrimination in a multiobject bipolar joint transform correlator,” Opt. Laser Technol. 24, 45–50 (1992).
[CrossRef]

A. Bal, M. S. Alam, “Feature extraction technique based on Hopfield neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 343–348 (2004).
[CrossRef]

A. Bal, M. S. Alam, A. El-Saba, “Optical fingerprint identification using cellular neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 349–355 (2004).
[CrossRef]

Bal, A.

O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).

A. Bal, M. S. Alam, “Feature extraction technique based on Hopfield neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 343–348 (2004).
[CrossRef]

A. Bal, M. S. Alam, A. El-Saba, “Optical fingerprint identification using cellular neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 349–355 (2004).
[CrossRef]

Beale, M.

T. M. Hagan, H. B. Demuth, M. Beale, Neural Networks Design (PWS-Kent, Boston, Mass., 1995).

Bolle, R.

L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
[CrossRef]

Cheng, F.

Cline, J. D.

S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).

Demuth, H. B.

T. M. Hagan, H. B. Demuth, M. Beale, Neural Networks Design (PWS-Kent, Boston, Mass., 1995).

El-Saba, A.

A. Bal, M. S. Alam, A. El-Saba, “Optical fingerprint identification using cellular neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 349–355 (2004).
[CrossRef]

Fiebig, M.

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

Gregory, D. A.

Hagan, T. M.

T. M. Hagan, H. B. Demuth, M. Beale, Neural Networks Design (PWS-Kent, Boston, Mass., 1995).

Hamlyn, G.

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

Hassebrook, L.

Hong, L.

L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
[CrossRef]

Jain, A.

L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
[CrossRef]

Javidi, B.

Kabrisky, M.

S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).

Karim, M. A.

M. S. Alam, M. A. Karim, “Fringe-adjusted joint transform correlation,” Appl. Opt. 32, 4344–4350 (1993).
[CrossRef] [PubMed]

M. S. Alam, M. A. Karim, “Improved correlation discrimination in a multiobject bipolar joint transform correlator,” Opt. Laser Technol. 24, 45–50 (1992).
[CrossRef]

Kumar, B. V. K. V.

B. V. K. V. Kumar, L. Hassebrook, “Performance measures for correlation filters,” Appl. Opt. 29, 2997–3001 (1990).
[CrossRef] [PubMed]

R. Singh, B. V. K. V. Kumar, “Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification,” in Algorithms for Synthetic Aperture Radar Imagery IX, E. G. Zelnio, ed., Proc. SPIE4727, 265–276 (2002).
[CrossRef]

Kuo, C.

Mahalanobis, A.

A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
[CrossRef]

Mercimek, M.

O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).

Miller, P. C.

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

Nagata, T.

Nevel, A. V.

A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
[CrossRef]

Pankanti, S.

L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
[CrossRef]

Rogers, S. K.

S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).

Royce, M.

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

Saatci, E.

E. Saatci, V. Tavsanoglu, “Fingerprint image enhancement using CNN Gabor-type filters,” in Proceedings of the Seventh IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA ’02) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 2002), pp. 377–382.
[CrossRef]

Sims, A. R.

A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
[CrossRef]

Singh, R.

R. Singh, B. V. K. V. Kumar, “Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification,” in Algorithms for Synthetic Aperture Radar Imagery IX, E. G. Zelnio, ed., Proc. SPIE4727, 265–276 (2002).
[CrossRef]

Tang, Q.

Tavsanoglu, V.

E. Saatci, V. Tavsanoglu, “Fingerprint image enhancement using CNN Gabor-type filters,” in Proceedings of the Seventh IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA ’02) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 2002), pp. 377–382.
[CrossRef]

Ucan, O. N.

O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).

Virgo, P.

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

Yu, F. T. S.

Appl. Opt. (6)

J. Elect. Electron. (1)

O. N. Ucan, A. Bal, M. Mercimek, “Corner detection using dynamic neural networks,” J. Elect. Electron. 2, 537–539 (2002).

Opt. Eng. (4)

P. C. Miller, M. Royce, P. Virgo, M. Fiebig, G. Hamlyn, “Evaluation of an optical correlator automatic target recognition system for acquisition and tracking in densely cluttered natural scenes,” Opt. Eng. 38, 1814–1825 (1999).
[CrossRef]

S. K. Rogers, J. D. Cline, M. Kabrisky, “New binarization techniques for joint transform correlation,” Opt. Eng. 29, 1018–1093 (1990).

M. S. Alam, “Deblurring using fringe-adjusted joint transform correlation,” Opt. Eng. 37, 556–564 (1998).
[CrossRef]

A. Mahalanobis, A. R. Sims, A. V. Nevel, “Signal-to-clutter measure for measuring automatic target recognition performance using complimentary eigenvalue distribution analysis,” Opt. Eng. 42, 1144–1151 (2003).
[CrossRef]

Opt. Laser Technol. (1)

M. S. Alam, M. A. Karim, “Improved correlation discrimination in a multiobject bipolar joint transform correlator,” Opt. Laser Technol. 24, 45–50 (1992).
[CrossRef]

Other (6)

R. Singh, B. V. K. V. Kumar, “Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification,” in Algorithms for Synthetic Aperture Radar Imagery IX, E. G. Zelnio, ed., Proc. SPIE4727, 265–276 (2002).
[CrossRef]

A. Bal, M. S. Alam, A. El-Saba, “Optical fingerprint identification using cellular neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 349–355 (2004).
[CrossRef]

T. M. Hagan, H. B. Demuth, M. Beale, Neural Networks Design (PWS-Kent, Boston, Mass., 1995).

A. Bal, M. S. Alam, “Feature extraction technique based on Hopfield neural network and joint transform correlation,” in Optical Information Systems II, B. Javidi, D. Psaltis, eds., Proc. SPIE5557, 343–348 (2004).
[CrossRef]

L. Hong, A. Jain, S. Pankanti, R. Bolle, “Fingerprint enhancement,” in Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1996), pp. 202–207.
[CrossRef]

E. Saatci, V. Tavsanoglu, “Fingerprint image enhancement using CNN Gabor-type filters,” in Proceedings of the Seventh IEEE International Workshop on Cellular Neural Networks and Their Applications (CNNA ’02) (Institute of Electrical and Electronics Engineers, Piscataway, N.J., 2002), pp. 377–382.
[CrossRef]

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 (7)

Fig. 1
Fig. 1

Supervised filtering architecture.

Fig. 2
Fig. 2

Fringe-adjusted JTC architecture.

Fig. 3
Fig. 3

Fingerprint enhancement process by supervised filtering technique: (a) original image and (b) enhanced image.

Fig. 4
Fig. 4

Fingerprint verification: (a) input joint image, (b) 2D correlation output, (c) 3D correlation output.

Fig. 5
Fig. 5

Fingerprint verification: (a) enhanced input joint image, (b) 2D correlation output, (c) 3D correlation output.

Fig. 6
Fig. 6

Fingerprint identification: (a) input joint image, (b) 2D correlation output, (c) 3D correlation output.

Fig. 7
Fig. 7

Fingerprint identification: (a) enhanced input joint image, (b) 2D correlation output, (c) 3D correlation output.

Tables (2)

Tables Icon

Table 1 Verification Performance Parameters

Tables Icon

Table 2 Identification Performance Parameters

Equations (23)

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

a m , n ( t + 1 ) = f ( ( i = - s s j = - s s h i , j a m + i , n + j ( t ) ) + b ) ,
a m , n ( 0 ) = p ,
f ( x ) = { - 1 x - 1 x - 1 < x < 1 1 x 1 .
E = ( 1 / 2 ) m n [ a m , n ( t + 1 ) - d m , n ] 2 .
h ( t + 1 ) = h ( t ) - η E ( t ) h ( t ) ,
b ( t + 1 ) = b ( t ) - η E ( t ) b ( t ) ,
E h = E c ( t ) c ( t ) h ,
E b = E c ( t ) c ( t ) b .
c m , n ( t ) = i = - s s j = - s s h i , j a m + i , n + j ( t ) + b .
c ( t ) h = a ( t ) ,             c ( t ) b = 1.
E c ( t ) = - 2 f ( c ( t ) ) ( d - a ( t + 1 ) ) ,
h ( t + 1 ) = h ( t ) - 2 η f ( c ( t ) ) a m , n ( t ) ( d - a ( t + 1 ) ) ,
b ( t + 1 ) = b ( t ) - 2 η f ( c ( t ) ) ( d - a ( t + 1 ) ) .
f ( x , y ) = r ( x , y + y 0 ) + i = 1 n t i ( x - x i , y - y i ) + n ( x , y - y 0 ) ,
F ( u , v ) 2 = R ( u , v ) 2 + i = 1 n T i ( u , v ) 2 + N ( u , v ) 2 + 2 i = 1 n T i ( u , v ) × R ( u , v ) cos [ ϕ t i ( u , v ) - ϕ r ( u , v ) - u x i - v y i - 2 v y 0 ] + 2 R ( u , v ) N ( u , v ) cos [ ϕ r ( u , v ) - ϕ n ( u , v ) + 2 v y 0 ) ] + 2 i = 1 n T i ( u , v ) N ( u , v ) cos [ ϕ t i ( u , v ) - ϕ n ( u , v ) - u x i - v y i ] + 2 i = 1 n k = 1 k 1 n T i ( u , v ) T k ( u , v ) × cos [ ϕ t i ( u , v ) - ϕ k ( u , v ) - u x i + u x k - v y i + v y k ] ,
P ( u , v ) = F ( u , v ) 2 - T ( u , v ) 2 - R ( u , v ) 2 = 2 i = 1 n T , ( u , v ) R ( u , v ) cos [ ϕ u ( u , v ) - ϕ r ( u , v ) - u x i - v y i - 2 v y 0 ] + 2 R ( u , v )     N ( u , v ) cos [ ϕ r ( u , v ) - ϕ n ( u , v ) - 2 v y 0 ] .
H ( u , v ) = C ( u , v ) [ D ( u , v ) + R ( u , v ) 2 ] - 1 ,
H ( u , v ) R ( u , v ) - 2 .
O ( u , v ) = H ( u , v ) × P ( u , v ) R ( u , v ) - 2 × P ( u , v ) .
PCE = P ( x , y ) 2 E p ,
E p = x y p ( x , y ) 2 .
PSR = p ( x , y ) - μ σ ,
PCR = p ( x , y ) p ( x , y ) ,

Metrics