OSA's Digital Library

Applied Optics

Applied Optics


  • Vol. 40, Iss. 23 — Aug. 10, 2001
  • pp: 3843–3849

Cascaded linear shift-invariant processors in optical pattern recognition

Stuart Reed and Jeremy Coupland  »View Author Affiliations

Applied Optics, Vol. 40, Issue 23, pp. 3843-3849 (2001)

View Full Text Article

Enhanced HTML    Acrobat PDF (623 KB)

Browse Journals / Lookup Meetings

Browse by Journal and Year


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools



We study a cascade of linear shift-invariant processing modules (correlators), each augmented with a nonlinear threshold as a means to increase the performance of high-speed optical pattern recognition. This configuration is a special class of multilayer, feed-forward neural networks and has been proposed in the literature as a relatively fast best-guess classifier. However, it seems that, although cascaded correlation has been proposed in a number of specific pattern recognition problems, the importance of the configuration has been largely overlooked. We prove that the cascaded architecture is the exact structure that must be adopted if a multilayer feed-forward neural network is trained to produce a shift-invariant output. In contrast with more generalized multilayer networks, the approach is easily implemented in practice with optical techniques and is therefore ideally suited to the high-speed analysis of large images. We have trained a digital model of the system using a modified backpropagation algorithm with optimization using simulated annealing techniques. The resulting cascade has been applied to a defect recognition problem in the canning industry as a benchmark for comparison against a standard linear correlation filter, the minimum average correlation energy (MACE) filter. We show that the nonlinear performance of the cascade is a significant improvement over that of the linear MACE filter in this case.

© 2001 Optical Society of America

OCIS Codes
(070.2580) Fourier optics and signal processing : Paraxial wave optics
(070.4560) Fourier optics and signal processing : Data processing by optical means
(070.5010) Fourier optics and signal processing : Pattern recognition
(100.1160) Image processing : Analog optical image processing

Original Manuscript: November 17, 2000
Revised Manuscript: March 22, 2001
Published: August 10, 2001

Stuart Reed and Jeremy Coupland, "Cascaded linear shift-invariant processors in optical pattern recognition," Appl. Opt. 40, 3843-3849 (2001)

Sort:  Author  |  Year  |  Journal  |  Reset  


  1. D. Casasent, L. M. Nieberg, “Classifier and shift-invariant automatic target recognition,” Neural Networks 8, 1117–1129 (1995). [CrossRef]
  2. X.-Y. Su, G.-S. Zhang, L.-R. Guo, “Phase-only composite filter,” Opt. Eng. 26, 520–523 (1987). [CrossRef]
  3. S.-C. B. Lo, S.-L. A. Lou, J.-S. Lin, M. T. Freedman, M. V. Chien, S. K. Mun, “Artificial convolution neural network techniques and applications for lung nodule detection,” IEEE Trans. Med. Imaging 14, 711–718 (1995). [CrossRef] [PubMed]
  4. J. W. Goodman, Introduction to Fourier Optics, 2nd ed. (McGraw-Hill, New York, 1996).
  5. C. L. Giles, T. Maxwell, “Learning, invariance, and generalization in high-order neural networks,” Appl. Opt. 26, 4972–4978 (1987). [CrossRef] [PubMed]
  6. S. J. Perantonis, P. J. G. Lisboa, “Translation, rotation and scale invariant pattern recognition by high-order neural networks and moment classifiers,” IEEE Trans. Neural Networks 3, 241–251 (1992). [CrossRef]
  7. M. D. Richard, R. P. Lippmann, “Neural network classifiers estimate Bayesian a posteriori probabilities,” Neural Comput. 3, 461–483 (1991). [CrossRef]
  8. F. Kanaya, S. Miyake, “Bayes statistical behavior and valid generalization of pattern classifying neural networks,” IEEE Trans. Neural Networks 2, 471–475 (1991). [CrossRef]
  9. J. Shamir, H. J. Caulfield, R. B. Johnson, “Massive holographic interconnection networks and their limitations,” Appl. Opt. 28, 311–324 (1989). [CrossRef] [PubMed]
  10. M. A. Neifeld, “Optical dual-scale architecture for neural image recognition,” Appl. Opt. 34, 5920–5927 (1995). [CrossRef] [PubMed]
  11. D. Casasent, “Unified synthetic discriminant function computation formulation,” Appl. Opt. 23, 1620–1627 (1984). [CrossRef]
  12. H. J. Caulfield, W. T. Maloney, “Improved discrimination in optical character recognition,” Appl. Opt. 8, 2354–2356 (1969). [CrossRef] [PubMed]
  13. B. V. K. Vijaya Kumar, “Minimum variance synthetic discriminant functions,” J. Opt. Soc. Am. A 3, 1579–1584 (1986).
  14. B. Javidi, “Nonlinear joint power spectrum based optical correlation,” Appl. Opt. 28, 2358–2367 (1989). [CrossRef] [PubMed]
  15. K. Fukushima, “Cognitron: a self-organizing multilayered neural network model,” Biol. Cybern. 20, 121–136 (1975). [CrossRef] [PubMed]
  16. K. Fukushima, “Neocognitron: a self-organizing multilayered neural network model for a mechanism of pattern recognition unaffected by shift in position,” Biol. Cybern. 36, 193–202 (1980). [CrossRef]
  17. B. Sahiner, H.-P. Chan, N. Petrick, D. Wei, M. A. Helvie, D. D. Adler, M. M. Goodsitt, “Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images,” IEEE. Trans. Med. Imaging 15, 598–610 (1996). [CrossRef] [PubMed]
  18. P. D. Gader, J. R. Miramonti, Y. Won, P. Coffield, “Segmentation free shared weight networks for automatic vehicle detection,” Neural Networks 8, 1457–1473 (1995). [CrossRef]
  19. F. Dubois, “Nonlinear cascaded correlation processes to improve the performances of automatic spatial-frequency-selective filters in pattern recognition,” Appl. Opt. 35, 4589–4597 (1996). [CrossRef] [PubMed]
  20. D. Psaltis, J. Hong, “Shift-invariant optical associative memories,” Opt. Eng. 26, 10–15 (1987). [CrossRef]
  21. F. T. S. Yu, S. Jutamulia, “Implementation of symbolic substitution logic using optical associative memories,” Appl. Opt. 26, 2293–2294 (1987). [CrossRef] [PubMed]
  22. S. D. Goodman, W. T. Rhodes, “Symbolic substitution applications to image processing,” Appl. Opt. 27, 1708–1714 (1988). [CrossRef] [PubMed]
  23. S. Reed, J. M. Coupland, “Statistical performance of cascaded shift invariant processing,” Appl. Opt. 39, 5949–5955 (2000). [CrossRef]
  24. S. Reed, J. M. Coupland, “Rotation invariance using cascaded optical processing architectures,” Asian J. Phys. 8, 421–429 (1999).
  25. W. K. Pratt, Digital Image Processing, 2nd ed. (Wiley, New York, 1991).
  26. R. A. Horn, C. R. Johnson, Matrix Analysis (Cambridge U. Press, Cambridge, UK, 1985). [CrossRef]
  27. E. Barnard, E. C. Botha, “Back-propagation uses prior information efficiently,” IEEE Trans. Neural Networks 4, 794–802 (1993). [CrossRef]
  28. S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi, “Optimisation by simulated annealing,” Science 220, 671–680 (1983). [CrossRef] [PubMed]
  29. A. Mahalanobis, B. V. K. Vijaya Kumar, D. Casasent, “Minimum average correlation energy filters,” Appl. Opt. 26, 3633–3640 (1987).

Cited By

Alert me when this paper is cited

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited