OSA's Digital Library

Applied Optics

Applied Optics


  • Vol. 42, Iss. 23 — Aug. 10, 2003
  • pp: 4658–4662

Nonlinear Filter for Pattern Recognition Invariant to Illumination and to Out-of-Plane Rotations

Daniel Lefebvre, Henri H. Arsenault, and Sébastien Roy  »View Author Affiliations

Applied Optics, Vol. 42, Issue 23, pp. 4658-4662 (2003)

View Full Text Article

Acrobat PDF (383 KB)

Browse Journals / Lookup Meetings

Browse by Journal and Year


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools



Automatic target recognition in uncontrolled conditions is a difficult task because many parameters are involved. This study deals with the recognition of targets under limited out-of-plane rotations while maintaining invariance to ambient light illumination. Contrast invariance is achieved by using the recently developed locally adaptive contrast-invariant filter, a method that yields correlation peaks whose values are invariant under any linear transformation of intensity. To reduce the sensitivity to the orientation of the object we replace the reference in the nonlinear filter by a synthetic discriminant filter. The range used for out-of-plane rotations was 40 degrees with a depression angle of 20 degrees. We present results for unsegmented targets on complex backgrounds with the presence of false targets.

© 2003 Optical Society of America

OCIS Codes
(070.0070) Fourier optics and signal processing : Fourier optics and signal processing
(070.4550) Fourier optics and signal processing : Correlators
(100.2000) Image processing : Digital image processing
(100.5010) Image processing : Pattern recognition
(150.2950) Machine vision : Illumination

Daniel Lefebvre, Henri H. Arsenault, and Sébastien Roy, "Nonlinear Filter for Pattern Recognition Invariant to Illumination and to Out-of-Plane Rotations," Appl. Opt. 42, 4658-4662 (2003)

Sort:  Author  |  Year  |  Journal  |  Reset


  1. F. M. Dickey and L. A. Romero, “Normalized correlation for pattern recognition,” Opt. Lett. 16, 1186–1188 (1991).
  2. B. A. Kast and F. M. Dickey, “Normalization of correlators,” in Optical Information Processing Systems and Architectures III, B. Javidi, ed., Proc. Soc. Photo-Opt. Instrum. Eng. 1564, 34–42 (1991).
  3. R. Kotynski and K. Chalasinska-Macukow, “Normalization of correlation filter based on the Hölder’s inequality,” in Optics in Computing ’98, P. H. Chavel, D. A. Miller, and H. Thienpont, eds., Proc. Soc. Photo Opt. Instrum. Eng. 3490, 195–198 (1998).
  4. R. Kotynski and K. Chalasinska-Macukow, “Multi-object intensity-invariant pattern recognition with an optimum processor for correlated noise,” in 18th Congress of the International Commission for Optics, A. J. Glass, J. W. Goodman, M. Chang, and A. H. Guenther, eds., Proc. Soc. Photo-Opt. Instrum. Eng. 3749, 316–317 (1999).
  5. H. H. Arsenault and C. Belisle, “Contrast-invariant pattern recognition using circular harmonic component,” Appl. Opt. 24, 2072–2075 (1985).
  6. P. Garcia-Martinez, H. H. Arsenault, and C. Ferreira, “Binary image decomposition for intensity-invariant optical nonlinear correlation,” in Optics in Computing 2000, R. A. Lessard and T. V. Galstian, eds., Proc. Soc. Photo-Opt. Instrum. Eng. 4089, 433–438 (2000).
  7. H. H. Arsenault and D. Lefebvre, “Homomorphic cameo filter for pattern recognition that is invariant with change of illumination,” Opt. Lett. 25, 1567–1569 (2000).
  8. K. Chalasinska-Macukow, F. Turon, M. J. Yzuel, and J. Campos, “Contrast performance of pure phase correlation,” J. Opt. Soc. Am. A 24, 71–75 (1993).
  9. C. Minetti, F. Dubois, and Jean-Claude Legros, “Reduction of the correlation sensitivity to the changes of the input illumination by post processing based on the correlation statistics,” Appl. Opt. 41, 3453–3460 (2002).
  10. S. Zhang and M. A. Karim, “Illumination invariant pattern recognition with joint-transform-correlator-based morphological correlation,” Appl. Opt. 38, 7228–7237 (1999).
  11. H. H. Arsenault, Y. Sheng, and J. Bulabois, “Modified composite filter for pattern recognition in presence of noise with a non-zero mean,” Opt. Commun. 63, 15–20 (1987).
  12. D. Lefebvre, H. H. Arsenault, P. Garcia-Martinez, and C. Ferreira, “Recognition of unsegmented targets invariant under transformations of intensity,” Appl. Opt. 41, 6135–6142 (2002).
  13. J. B. Burns, R. S. Weiss, and E. M. Riseman, “View variation of point-set and line-segment features,” IEEE Transactions on Pattern Anal. Mach. Intell. PAMI-15, 51–68 (1993).
  14. D. Casasent, W. Rozzi, and D. Fetterly, “Correlation synthetic discriminant functions for object recognition and classification in high clutter,” Proc. SPIE 575, 126–136 (1985).
  15. Y. Li and J. Rosen, “Three-dimensional pattern recognition with a single two-dimensional synthetic reference function,” Appl. Opt. 39, 1251–1259 (2000).
  16. J. Rosen, “Three-dimensional electro-optical correlation,” J. Opt. Soc. Am. A 15, 430–436 (1998).
  17. J. Rosen, “Three-dimensional joint transform correlator,” Appl. Opt. 37, 7538–7544 (1998).
  18. B. Javidi, J. Li, and Q. Tang, “Optical implementation of neural networks for face recognition by the use of nonlinear joint transform correlators,” Appl. Opt. 34, 3950–3962 (1995).
  19. L. Neiberg and D. P. Casasent, “Feature space trajectory (FST) classifier neural network,” in Intelligent Robots and Computer Vision 13: Algorithms and Computer Vision, D. P. Casasent, ed., Proc. SPIE 2353, 276–292 (1994).
  20. S. Roy and H. H. Arsenault, “Shift, scale and pose invariant object recognition using wedge sampling and a feature space trajectory classifier,” J. Mod. Opt. 50, 285–297 (2003).
  21. S. Roy, H. H. Arsenault, and D. Lefebvre, “Invariant object recognition under three-dimensional rotations and changes of scale,” Opt. Eng. 42, 813–821 (2003).

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