Abstract

While diffraction-pattern sampling has been widely applied in the classification of patterns, still its usage has been limited somewhat by the need to devise rather sophisticated algorithms. In this paper we describe sorting or classification of a variety of patterns with commercially available neural-network software together with the ring–wedge photodetector to supply optical transform data for the input neurons. With this combination of neural networks and diffraction-pattern sampling it is no longer necessary to write specialized software. The training and testing methodology is carried out for this new system, and excellent results are obtained for sorting thumbprints. In sorting thumbprints the neural network can be trained for orientation-independent or wide-scale size-independent classifications by use of ring-only or wedge-only input neurons, respectively. Separate experiments are described for the sorting of particulates. Again, these are cases in which writing appropriate software based on diffraction theory would be extremely difficult. Two interesting novel neural networks are obtained: one is for real-time control of a submicrometer colloidal suspension of CdS, and the second is for concentration measurements of 2.02-μm polyvinyltoulene spheres in methyl alcohol. Widespread new applications are predicted for this hybrid system that combines diffraction-pattern sampling and the neural network.

© 1994 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. C. A. Taylor, H. Lipson, Optical Transforms: Their Preparation and Application to X-Ray Diffraction Problems (Bell, London, 1964).
  2. J. R. Leger, S. H. Lee, “Signal processing using hybrid systems,” in Optical Transforms, H. Stark, ed. (Academic, London, 1972).
  3. Henry Stark, ed., Applications of Optical Fourier Transforms (Academic, New York, 1982), pp. 1–30, 162–180.
  4. G. G. Lendaris, L. L. Stanley, “Diffraction pattern sampling for automatic pattern recognition,” Proc. IEEE 58, 198 (1970).
    [CrossRef]
  5. N. George, J. T. Thomasson, A. Spindel, “Photodetector light pattern detector,” U.S. patent3,689,772 (5September1972)
  6. N. George, H. L. Kasdan, “Diffraction pattern sampling for recognition and metrology,” in Electro-Optical Systems Design Conference 1975, Proceedings of Anaheim International Laser Exposition (Industrial and Scientific Conference Management, Chicago, Ill., 1975), pp. 494–503.
  7. H. Kasdan, D. Mead, “Out of the laboratory and into the factory,” in Proceedings of Electro-Optical System Design (Industrial and Scientific Conference Management, Chicago, Ill., 1975), p. 248.
  8. G. Gonesbet, G. Gréhan, eds., Optical Particle Sizing (Plenum, New York, 1988).
  9. D. E. Glover, “A hybrid optical Fourier/electronic neurocomputer machine vision inspection system,” in Proceedings of Vision ’88 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1988), Vol. 2, pp. 8.17–8.104.
  10. D. Clark, “An optical feature extractor for machine vision inspection,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 17.23–17.50.
  11. D. Clark, D. P. Casasent, “Practical optical Fourier analysis for high speed inspection,” Opt. Eng. 27, 365–371 (1988).
  12. J. Belilove, “Optical processing feature extraction, a survey in the consumable goods industry,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 14.1–14.25.
  13. B. Widrow, study director, DARPA Neural Network Study (AFCEA International, Fairfax, Va., 1988).
  14. N. George, S. G. Wang, D. L. Venable, “Pattern recognition using the ring–wedge detector and neural-network software,” in Optical Pattern Recognition II, H. J. Caulfield, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1134, 96–106 (1989).
  15. J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).
  16. D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).
  17. B. Telfer, D. Casasent, “Ho–Kashyap optical associative processors,” Appl. Opt. 29, 1191–1202 (1990).
    [CrossRef] [PubMed]
  18. B. Telfer, D. Casasent, “Minimum-cost Ho–Kashyap associative processor for piecewise-hyperspherical classification,” in Proceedings of the International Joint Conference on Neural Networks, M. Caudill, ed. (Institute of Electrical and Electronics Engineers, New York, 1991), pp. 1189–1194.
  19. D. Casasent, E. Barnard, “Adaptive clustering optical neural net,” Appl. Opt. 29, 2603–2615 (1990).
    [CrossRef] [PubMed]
  20. D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing, (MIT Press, Cambridge, 1988), Vols. 1 and 2.
  21. R. P. Lippmann, “An introduction to computing with neural nets,” IEEE Trans. Acoust. Speech Signal Process ASSP-4, 4–22 (1987).
  22. NeuralWorks, Revision 2.00 (Neural Ware, Inc., Sewickley, Pa., 1988).
  23. Automatic Recognitionand Control, Inc., 24 Widewaters Lane, Pittsford, N.Y. 14534.
  24. S. Voyutsky, Colloid Chemistry (Mir, Moscow, 1978), p. 110.

1990 (2)

1988 (1)

D. Clark, D. P. Casasent, “Practical optical Fourier analysis for high speed inspection,” Opt. Eng. 27, 365–371 (1988).

1987 (1)

R. P. Lippmann, “An introduction to computing with neural nets,” IEEE Trans. Acoust. Speech Signal Process ASSP-4, 4–22 (1987).

1970 (1)

G. G. Lendaris, L. L. Stanley, “Diffraction pattern sampling for automatic pattern recognition,” Proc. IEEE 58, 198 (1970).
[CrossRef]

Barnard, E.

Belilove, J.

J. Belilove, “Optical processing feature extraction, a survey in the consumable goods industry,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 14.1–14.25.

Cappiello, G.

D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).

Casasent, D.

B. Telfer, D. Casasent, “Ho–Kashyap optical associative processors,” Appl. Opt. 29, 1191–1202 (1990).
[CrossRef] [PubMed]

D. Casasent, E. Barnard, “Adaptive clustering optical neural net,” Appl. Opt. 29, 2603–2615 (1990).
[CrossRef] [PubMed]

B. Telfer, D. Casasent, “Minimum-cost Ho–Kashyap associative processor for piecewise-hyperspherical classification,” in Proceedings of the International Joint Conference on Neural Networks, M. Caudill, ed. (Institute of Electrical and Electronics Engineers, New York, 1991), pp. 1189–1194.

Casasent, D. P.

D. Clark, D. P. Casasent, “Practical optical Fourier analysis for high speed inspection,” Opt. Eng. 27, 365–371 (1988).

Clark, D.

D. Clark, D. P. Casasent, “Practical optical Fourier analysis for high speed inspection,” Opt. Eng. 27, 365–371 (1988).

D. Clark, “An optical feature extractor for machine vision inspection,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 17.23–17.50.

Coppeta, D.

D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).

Figue, J.

J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).

George, N.

N. George, S. G. Wang, D. L. Venable, “Pattern recognition using the ring–wedge detector and neural-network software,” in Optical Pattern Recognition II, H. J. Caulfield, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1134, 96–106 (1989).

N. George, H. L. Kasdan, “Diffraction pattern sampling for recognition and metrology,” in Electro-Optical Systems Design Conference 1975, Proceedings of Anaheim International Laser Exposition (Industrial and Scientific Conference Management, Chicago, Ill., 1975), pp. 494–503.

N. George, J. T. Thomasson, A. Spindel, “Photodetector light pattern detector,” U.S. patent3,689,772 (5September1972)

Glover, D. E.

D. E. Glover, “A hybrid optical Fourier/electronic neurocomputer machine vision inspection system,” in Proceedings of Vision ’88 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1988), Vol. 2, pp. 8.17–8.104.

Goodwin, D. B.

D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).

Govignon, J.

D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).

Huignard, J.

J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).

Kasdan, H.

H. Kasdan, D. Mead, “Out of the laboratory and into the factory,” in Proceedings of Electro-Optical System Design (Industrial and Scientific Conference Management, Chicago, Ill., 1975), p. 248.

Kasdan, H. L.

N. George, H. L. Kasdan, “Diffraction pattern sampling for recognition and metrology,” in Electro-Optical Systems Design Conference 1975, Proceedings of Anaheim International Laser Exposition (Industrial and Scientific Conference Management, Chicago, Ill., 1975), pp. 494–503.

Lee, S. H.

J. R. Leger, S. H. Lee, “Signal processing using hybrid systems,” in Optical Transforms, H. Stark, ed. (Academic, London, 1972).

Leger, J. R.

J. R. Leger, S. H. Lee, “Signal processing using hybrid systems,” in Optical Transforms, H. Stark, ed. (Academic, London, 1972).

Lendaris, G. G.

G. G. Lendaris, L. L. Stanley, “Diffraction pattern sampling for automatic pattern recognition,” Proc. IEEE 58, 198 (1970).
[CrossRef]

Lippmann, R. P.

R. P. Lippmann, “An introduction to computing with neural nets,” IEEE Trans. Acoust. Speech Signal Process ASSP-4, 4–22 (1987).

Lipson, H.

C. A. Taylor, H. Lipson, Optical Transforms: Their Preparation and Application to X-Ray Diffraction Problems (Bell, London, 1964).

McClelland, J. L.

D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing, (MIT Press, Cambridge, 1988), Vols. 1 and 2.

Mead, D.

H. Kasdan, D. Mead, “Out of the laboratory and into the factory,” in Proceedings of Electro-Optical System Design (Industrial and Scientific Conference Management, Chicago, Ill., 1975), p. 248.

Rajbenbach, H.

J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).

Refregiér, P.

J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).

Rumelhart, D. E.

D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing, (MIT Press, Cambridge, 1988), Vols. 1 and 2.

Spindel, A.

N. George, J. T. Thomasson, A. Spindel, “Photodetector light pattern detector,” U.S. patent3,689,772 (5September1972)

Stanley, L. L.

G. G. Lendaris, L. L. Stanley, “Diffraction pattern sampling for automatic pattern recognition,” Proc. IEEE 58, 198 (1970).
[CrossRef]

Taylor, C. A.

C. A. Taylor, H. Lipson, Optical Transforms: Their Preparation and Application to X-Ray Diffraction Problems (Bell, London, 1964).

Telfer, B.

B. Telfer, D. Casasent, “Ho–Kashyap optical associative processors,” Appl. Opt. 29, 1191–1202 (1990).
[CrossRef] [PubMed]

B. Telfer, D. Casasent, “Minimum-cost Ho–Kashyap associative processor for piecewise-hyperspherical classification,” in Proceedings of the International Joint Conference on Neural Networks, M. Caudill, ed. (Institute of Electrical and Electronics Engineers, New York, 1991), pp. 1189–1194.

Thomasson, J. T.

N. George, J. T. Thomasson, A. Spindel, “Photodetector light pattern detector,” U.S. patent3,689,772 (5September1972)

Venable, D. L.

N. George, S. G. Wang, D. L. Venable, “Pattern recognition using the ring–wedge detector and neural-network software,” in Optical Pattern Recognition II, H. J. Caulfield, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1134, 96–106 (1989).

Voyutsky, S.

S. Voyutsky, Colloid Chemistry (Mir, Moscow, 1978), p. 110.

Wang, S. G.

N. George, S. G. Wang, D. L. Venable, “Pattern recognition using the ring–wedge detector and neural-network software,” in Optical Pattern Recognition II, H. J. Caulfield, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1134, 96–106 (1989).

Appl. Opt. (2)

IEEE Trans. Acoust. Speech Signal Process (1)

R. P. Lippmann, “An introduction to computing with neural nets,” IEEE Trans. Acoust. Speech Signal Process ASSP-4, 4–22 (1987).

Opt. Eng. (1)

D. Clark, D. P. Casasent, “Practical optical Fourier analysis for high speed inspection,” Opt. Eng. 27, 365–371 (1988).

Proc. IEEE (1)

G. G. Lendaris, L. L. Stanley, “Diffraction pattern sampling for automatic pattern recognition,” Proc. IEEE 58, 198 (1970).
[CrossRef]

Other (19)

N. George, J. T. Thomasson, A. Spindel, “Photodetector light pattern detector,” U.S. patent3,689,772 (5September1972)

N. George, H. L. Kasdan, “Diffraction pattern sampling for recognition and metrology,” in Electro-Optical Systems Design Conference 1975, Proceedings of Anaheim International Laser Exposition (Industrial and Scientific Conference Management, Chicago, Ill., 1975), pp. 494–503.

H. Kasdan, D. Mead, “Out of the laboratory and into the factory,” in Proceedings of Electro-Optical System Design (Industrial and Scientific Conference Management, Chicago, Ill., 1975), p. 248.

G. Gonesbet, G. Gréhan, eds., Optical Particle Sizing (Plenum, New York, 1988).

D. E. Glover, “A hybrid optical Fourier/electronic neurocomputer machine vision inspection system,” in Proceedings of Vision ’88 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1988), Vol. 2, pp. 8.17–8.104.

D. Clark, “An optical feature extractor for machine vision inspection,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 17.23–17.50.

J. Belilove, “Optical processing feature extraction, a survey in the consumable goods industry,” in Proceedings of Vision ‘87 Conference (Society of Manufacturing Engineering, Dearborn, Mich., 1987), Vol. 1, pp. 14.1–14.25.

B. Widrow, study director, DARPA Neural Network Study (AFCEA International, Fairfax, Va., 1988).

N. George, S. G. Wang, D. L. Venable, “Pattern recognition using the ring–wedge detector and neural-network software,” in Optical Pattern Recognition II, H. J. Caulfield, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1134, 96–106 (1989).

J. Figue, P. Refregiér, H. Rajbenbach, J. Huignard, “Neural optoelectronic correlator for pattern recognition,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 550–561 (1991).

D. B. Goodwin, G. Cappiello, D. Coppeta, J. Govignon, “Hybrid digital/optical ATR system,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng.1564, 539–549 (1991).

D. E. Rumelhart, J. L. McClelland, and the PDP Research Group, Parallel Distributed Processing, (MIT Press, Cambridge, 1988), Vols. 1 and 2.

NeuralWorks, Revision 2.00 (Neural Ware, Inc., Sewickley, Pa., 1988).

Automatic Recognitionand Control, Inc., 24 Widewaters Lane, Pittsford, N.Y. 14534.

S. Voyutsky, Colloid Chemistry (Mir, Moscow, 1978), p. 110.

B. Telfer, D. Casasent, “Minimum-cost Ho–Kashyap associative processor for piecewise-hyperspherical classification,” in Proceedings of the International Joint Conference on Neural Networks, M. Caudill, ed. (Institute of Electrical and Electronics Engineers, New York, 1991), pp. 1189–1194.

C. A. Taylor, H. Lipson, Optical Transforms: Their Preparation and Application to X-Ray Diffraction Problems (Bell, London, 1964).

J. R. Leger, S. H. Lee, “Signal processing using hybrid systems,” in Optical Transforms, H. Stark, ed. (Academic, London, 1972).

Henry Stark, ed., Applications of Optical Fourier Transforms (Academic, New York, 1982), pp. 1–30, 162–180.

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 (8)

Fig. 1
Fig. 1

Diffraction-pattern-sampling system incorporating the ring–wedge photodetector and neural-network software: O, input object, L, optical-transform lens, R/W, ring–wedge photodetector, NS, neural software, C, digital computer; A, amplifier and interface.

Fig. 2
Fig. 2

Thumbprints used in neural-network study: F1 to F8, reading from left to right.

Fig. 3
Fig. 3

Diffraction-pattern sample for F1 and F8 showing (left) the logarithm of optical intensity versus these ring number and (right) the intensity versus the wedge number.

Fig. 4
Fig. 4

Power spectral density versus spatial frequency for a suspension of CdS showing the settling with time. A filtered water sample is shown for comparison (▲). The aperture is 10 mm in diameter.

Fig. 5
Fig. 5

Error in output neurons versus the number of training cycles, showing excellent learning of data from Fig. 4.

Fig. 6
Fig. 6

Optical power (logarithmic) versus the ring number is shown for varying concentrations of 2.02-μm spheres in methyl alcohol for the learning set.

Fig. 7
Fig. 7

Concentration measurements of 2.02-μm spheres obtained by the single analog neuron: the degree of learning and the accuracy against the test set are shown for (a) 500 and (b) 2000 cycles (c.) of training.

Fig. 8
Fig. 8

Pattern classification for various concentrations of spheres in the learning and the test sets with multiple output neurons (see Subsection 4.B). Excellent quantitative accuracy is obtained.

Tables (4)

Tables Icon

Table 1 Fingerprint Recognition Showing the Number of Cycles Required for Learning and the Error-Rate Fraction as a Function of the Number of Sets Used in Training

Tables Icon

Table 2 Accuracy of the Testing Set for Eight Thumbprints When Five Learning Prints Are Useda

Tables Icon

Table 3 Thumbprint Classification Accuracy for a Large Independent Data Set of 160 Separate Thumbprints in the Testing with Only One Errora

Tables Icon

Table 4 Accuracy In Measuring Concentrations of 2.02-μm Spheres in Methyl Alcohol for the Test Samples L0–L7a

Metrics