Abstract

Optical pattern recognition under variations of illumination is an important issue. The sliced orthogonal nonlinear generalized (SONG) correlation has been proposed as an optical pattern recognition tool to discriminate with high efficiency between objects. But, at the same time, the SONG correlation is very sensitive to gray-scale image variations. In a previous work, we expanded the definition of the SONG correlation to the Weighted SONG (WSONG) correlation to modify the discrimination capability in a controlled way. Here, we propose to use the WSONG when pattern recognition is obtained by means of optical correlation under nonuniform illumination. The calculation of the WSONG correlation requires the summation of many linear correlations between binary images. To implement it optically, we use a time sequential joint transform correlator.

© 2002 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. J. W. Goodman, Introduction to Fourier Optics (McGraw-Hill, New York, 1996).
  2. B. G. Boone, Signal Processing using Optics: Fundamentals, Devices, Architectures, and Applications (Oxford University, New York, 1998).
  3. A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory, IT-10, 139–145 (1964).
    [CrossRef]
  4. C. S. Weaver, J. W. Goodman, “A technique for optically convolving two functions,” Appl. Opt. 5, 1248–1249 (1966).
    [CrossRef] [PubMed]
  5. P. Purswosumarto, F. T. S. Yu, “Robustness of joint transform correlator versus Vander Lugt correlator,” Opt. Eng. 36, 2775–2780 (1997).
    [CrossRef]
  6. Selected Papers on Optical Pattern Recognition Using Joint Transform Correlation, M. S. Alam, ed. SPIE Milestone Series, MS157 (1999).
  7. B. Javidi, J. Wang, Q. Tang, “Nonlinear joint transform correlators,” Pattern Recogn. 27, 523–542 (1999).
    [CrossRef]
  8. A. Tanone, C.-M. Uang, F. T. S. Yu, E. C. Tam, D. A. Gregory, “Effects of thresholding in joint-transform correlation,” Appl. Opt. 31, 4816–4822 (1992).
    [CrossRef] [PubMed]
  9. H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
    [CrossRef]
  10. E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
    [CrossRef]
  11. P. Garcia-Martinez, D. Mas, J. Garcia, C. Ferreira, “Nonlinear morphological correlation: optoelectronic implementation,” Appl. Opt. 37, 2112–2118 (1998).
    [CrossRef]
  12. P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
    [CrossRef]
  13. P. Maragos, “Morphological correlation and mean absolute error criteria,” IEEE Trans. Acoust., Speech Signal Process. 3, 1568–1571 (1989).
  14. W. C. Hasenplaugh, M. A. Neifeld, “Image binarization techniques for correlation-based pattern recognition,” Opt. Eng. 38, 1907–1917 (1999).
    [CrossRef]
  15. M. S. Alam, M. A. Karim, “Joint-transform correlation under varying illumination,” Appl. Opt. 32, 4351–4356 (1993).
    [CrossRef] [PubMed]
  16. S. Jutamulia, G. M. Storti, D. A. Gregory, J. C. Kirsch, “Illumination-independent high efficient joint-transform correlation,” Appl. Opt. 30, 4173–4175 (1991).
    [CrossRef] [PubMed]
  17. B. Javidi, J. Li, A. H. Fazlollahi, J. Horner, “Binary nonlinear joint transform correlator performance with different thresholding under unknown illumination conditions,” Appl. Opt. 34, 886–896 (1995).
    [CrossRef] [PubMed]
  18. P. Garcia-Martínez, H. H. Arsenault, “A correlation matrix representation using the sliced orthogonal nonlinear generalized decomposition,” Opt. Commun. 172, 181–192 (1999).
    [CrossRef]
  19. P. Garcia-Martínez, Ph. Réfrégier, H. H. Arsenault, C. Ferreira, “Maximum likelihood for target location in the presence of substitutive noise,” Appl. Opt. 40, 3855–3860 (2001).
    [CrossRef]
  20. M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
    [CrossRef]
  21. F. M. Dickey, L. A. Romero, “Normalized correlation for pattern recognition,” Opt. Lett. 16, 1186–1188 (1991).
    [CrossRef] [PubMed]
  22. O. Germain, P. Réfrégier, “Optimal snake-based segmentation of a random luminance target on a spatially disjoint background,” Opt. Lett. 22, 1845–1847 (1996).
    [CrossRef]
  23. S. Jutamulia, D. A. Gregory, “Soft blocking of the dc term in Fourier optical systems,” Opt. Eng. 37, 49–51 (1998).
    [CrossRef]

2002

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

2001

2000

P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
[CrossRef]

1999

W. C. Hasenplaugh, M. A. Neifeld, “Image binarization techniques for correlation-based pattern recognition,” Opt. Eng. 38, 1907–1917 (1999).
[CrossRef]

B. Javidi, J. Wang, Q. Tang, “Nonlinear joint transform correlators,” Pattern Recogn. 27, 523–542 (1999).
[CrossRef]

P. Garcia-Martínez, H. H. Arsenault, “A correlation matrix representation using the sliced orthogonal nonlinear generalized decomposition,” Opt. Commun. 172, 181–192 (1999).
[CrossRef]

1998

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

S. Jutamulia, D. A. Gregory, “Soft blocking of the dc term in Fourier optical systems,” Opt. Eng. 37, 49–51 (1998).
[CrossRef]

P. Garcia-Martinez, D. Mas, J. Garcia, C. Ferreira, “Nonlinear morphological correlation: optoelectronic implementation,” Appl. Opt. 37, 2112–2118 (1998).
[CrossRef]

1997

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

P. Purswosumarto, F. T. S. Yu, “Robustness of joint transform correlator versus Vander Lugt correlator,” Opt. Eng. 36, 2775–2780 (1997).
[CrossRef]

1996

O. Germain, P. Réfrégier, “Optimal snake-based segmentation of a random luminance target on a spatially disjoint background,” Opt. Lett. 22, 1845–1847 (1996).
[CrossRef]

1995

1993

1992

1991

1989

P. Maragos, “Morphological correlation and mean absolute error criteria,” IEEE Trans. Acoust., Speech Signal Process. 3, 1568–1571 (1989).

1966

1964

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory, IT-10, 139–145 (1964).
[CrossRef]

Alam, M. S.

Arsenault, H. H.

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

P. Garcia-Martínez, Ph. Réfrégier, H. H. Arsenault, C. Ferreira, “Maximum likelihood for target location in the presence of substitutive noise,” Appl. Opt. 40, 3855–3860 (2001).
[CrossRef]

P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
[CrossRef]

P. Garcia-Martínez, H. H. Arsenault, “A correlation matrix representation using the sliced orthogonal nonlinear generalized decomposition,” Opt. Commun. 172, 181–192 (1999).
[CrossRef]

Boone, B. G.

B. G. Boone, Signal Processing using Optics: Fundamentals, Devices, Architectures, and Applications (Oxford University, New York, 1998).

Chalasinska-Macukow, K.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Dickey, F. M.

Fazlollahi, A. H.

Ferreira, C.

Garcia, J.

Garcia-Martinez, P.

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
[CrossRef]

P. Garcia-Martinez, D. Mas, J. Garcia, C. Ferreira, “Nonlinear morphological correlation: optoelectronic implementation,” Appl. Opt. 37, 2112–2118 (1998).
[CrossRef]

Garcia-Martínez, P.

P. Garcia-Martínez, Ph. Réfrégier, H. H. Arsenault, C. Ferreira, “Maximum likelihood for target location in the presence of substitutive noise,” Appl. Opt. 40, 3855–3860 (2001).
[CrossRef]

P. Garcia-Martínez, H. H. Arsenault, “A correlation matrix representation using the sliced orthogonal nonlinear generalized decomposition,” Opt. Commun. 172, 181–192 (1999).
[CrossRef]

Germain, O.

O. Germain, P. Réfrégier, “Optimal snake-based segmentation of a random luminance target on a spatially disjoint background,” Opt. Lett. 22, 1845–1847 (1996).
[CrossRef]

Goodman, J. W.

Gregory, D. A.

Hasenplaugh, W. C.

W. C. Hasenplaugh, M. A. Neifeld, “Image binarization techniques for correlation-based pattern recognition,” Opt. Eng. 38, 1907–1917 (1999).
[CrossRef]

Hey, R.

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

Horner, J.

Javidi, B.

Jutamulia, S.

Karim, M. A.

Kirsch, J. C.

Kotynski, R.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Lefebvre, D.

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

Li, J.

Maragos, P.

P. Maragos, “Morphological correlation and mean absolute error criteria,” IEEE Trans. Acoust., Speech Signal Process. 3, 1568–1571 (1989).

Mas, D.

Millan, M. S.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Neifeld, M. A.

W. C. Hasenplaugh, M. A. Neifeld, “Image binarization techniques for correlation-based pattern recognition,” Opt. Eng. 38, 1907–1917 (1999).
[CrossRef]

Noharet, B.

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

Perez, E.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Purswosumarto, P.

P. Purswosumarto, F. T. S. Yu, “Robustness of joint transform correlator versus Vander Lugt correlator,” Opt. Eng. 36, 2775–2780 (1997).
[CrossRef]

Réfrégier, P.

O. Germain, P. Réfrégier, “Optimal snake-based segmentation of a random luminance target on a spatially disjoint background,” Opt. Lett. 22, 1845–1847 (1996).
[CrossRef]

Réfrégier, Ph.

Romero, L. A.

Roy, S.

P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
[CrossRef]

Sjöberg, H.

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

Storti, G. M.

Styczynski, K.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Tam, E. C.

Tang, Q.

B. Javidi, J. Wang, Q. Tang, “Nonlinear joint transform correlators,” Pattern Recogn. 27, 523–542 (1999).
[CrossRef]

Tanone, A.

Tejera, M.

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

Uang, C.-M.

Vander Lugt, A.

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory, IT-10, 139–145 (1964).
[CrossRef]

Wang, J.

B. Javidi, J. Wang, Q. Tang, “Nonlinear joint transform correlators,” Pattern Recogn. 27, 523–542 (1999).
[CrossRef]

Weaver, C. S.

Wosinski, L.

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

Yu, F. T. S.

P. Purswosumarto, F. T. S. Yu, “Robustness of joint transform correlator versus Vander Lugt correlator,” Opt. Eng. 36, 2775–2780 (1997).
[CrossRef]

A. Tanone, C.-M. Uang, F. T. S. Yu, E. C. Tam, D. A. Gregory, “Effects of thresholding in joint-transform correlation,” Appl. Opt. 31, 4816–4822 (1992).
[CrossRef] [PubMed]

Appl. Opt.

IEEE Trans. Acoust., Speech Signal Process.

P. Maragos, “Morphological correlation and mean absolute error criteria,” IEEE Trans. Acoust., Speech Signal Process. 3, 1568–1571 (1989).

IEEE Trans. Inf. Theory

A. Vander Lugt, “Signal Detection by Complex Spatial Filtering,” IEEE Trans. Inf. Theory, IT-10, 139–145 (1964).
[CrossRef]

J. Mod. Opt.

E. Perez, K. Chalasinska-Macukow, K. Styczynski, R. Kotynski, M. S. Millan, “Dual nonlinear correlator based on computer controlled joint transform processor: digital analysis and optical results,” J. Mod. Opt. 44, 1535–1552 (1997).
[CrossRef]

Opt. Commun.

M. Tejera, P. Garcia-Martinez, C. Ferreira, D. Lefebvre, H. H. Arsenault, “Weighted nonlinear correlation for controlled discrimination capability,” Opt. Commun. 201, 29–37 (2002).
[CrossRef]

P. Garcia-Martinez, H. H. Arsenault, S. Roy, “Optical implementation of the sliced orthogonal nonlinear generalized correlation for images degraded by nonoverlapping background noise,” Opt. Commun. 173, 185–193 (2000).
[CrossRef]

P. Garcia-Martínez, H. H. Arsenault, “A correlation matrix representation using the sliced orthogonal nonlinear generalized decomposition,” Opt. Commun. 172, 181–192 (1999).
[CrossRef]

Opt. Eng.

W. C. Hasenplaugh, M. A. Neifeld, “Image binarization techniques for correlation-based pattern recognition,” Opt. Eng. 38, 1907–1917 (1999).
[CrossRef]

H. Sjöberg, B. Noharet, L. Wosinski, R. Hey, “Compact optical correlator: preprocessing and filter encoding strategies applied to images with varying illumination,” Opt. Eng. 37, 1316–1324 (1998).
[CrossRef]

P. Purswosumarto, F. T. S. Yu, “Robustness of joint transform correlator versus Vander Lugt correlator,” Opt. Eng. 36, 2775–2780 (1997).
[CrossRef]

S. Jutamulia, D. A. Gregory, “Soft blocking of the dc term in Fourier optical systems,” Opt. Eng. 37, 49–51 (1998).
[CrossRef]

Opt. Lett.

F. M. Dickey, L. A. Romero, “Normalized correlation for pattern recognition,” Opt. Lett. 16, 1186–1188 (1991).
[CrossRef] [PubMed]

O. Germain, P. Réfrégier, “Optimal snake-based segmentation of a random luminance target on a spatially disjoint background,” Opt. Lett. 22, 1845–1847 (1996).
[CrossRef]

Pattern Recogn.

B. Javidi, J. Wang, Q. Tang, “Nonlinear joint transform correlators,” Pattern Recogn. 27, 523–542 (1999).
[CrossRef]

Other

Selected Papers on Optical Pattern Recognition Using Joint Transform Correlation, M. S. Alam, ed. SPIE Milestone Series, MS157 (1999).

J. W. Goodman, Introduction to Fourier Optics (McGraw-Hill, New York, 1996).

B. G. Boone, Signal Processing using Optics: Fundamentals, Devices, Architectures, and Applications (Oxford University, New York, 1998).

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

Diagram of the conversion from the weight matrix into a weight vector.

Fig. 2
Fig. 2

Classical joint transform correlator.

Fig. 3
Fig. 3

Block diagram of the opto-electronic WSONG correlation.

Fig. 4
Fig. 4

(a) Joint input scene containing the input scene (top) and the reference object (bottom) for the shadow effect illumination. (b) Joint input scene containing the input scene (top) with the nonuniform degraded image and the reference object (bottom).

Fig. 5
Fig. 5

Joint power spectra (JPS) example for the WSONG correlation.

Fig. 6
Fig. 6

Experimental output plane containing the optical linear correlation of the scene shown in Fig. 4(a): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Fig. 7
Fig. 7

Experimental output plane containing the optical SONG correlation of the scene shown in Fig. 4(a): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Fig. 8
Fig. 8

Experimental output plane containing the optical WSONG correlation of the scene shown in Fig. 4(a): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Fig. 9
Fig. 9

Experimental output plane containing the optical linear correlation of the scene shown in Fig. 4(b): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Fig. 10
Fig. 10

Experimental output plane containing the optical SONG correlation of the scene shown in Fig. 4(b): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Fig. 11
Fig. 11

Experimental output plane containing the optical WSONG correlation of the scene shown in Fig. 4(b): (a) Output correlation plane covering an area around the correlation peaks, (b) 3-D plots.

Equations (10)

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

eifx, y=1fx, y=i0fx, yi.
fx, y=i=0N-1 ieifx, y,
eifx, y, ejfx, y=δijeifx, y2.
gx, yfx, y=i=0N-1j=0N-1 ijeigx, yejfx, y.
Ωg,fx, y=i=0N-1j=0N-1 Wijeigx, yejfx, y.
Ωg,fx, y=i=0N-1j=0N-1 Rgfijx, y=ΘR0,0R0,1R0,N-1R1,0R1,1R1,N-1RN-1,0RN-1,1RN-1,N-1,
ΩgfPx, y=i=0N-1 eigx, yeifx, y.
gx, y=αx, yfx, y,
αx, y=1+Aλx, ylx,ly
JPSu, v=i=0N-1j=0N-1JPSiju, v=i=0N-1j=0N-1Wij|FTeigx, y +ejfx, y|2,

Metrics