Advertisement

Composite Correlation Filters for Detection of Geometrically Distorted Objects Using Noisy Training Images

  • Pablo M. Aguilar-González
  • Vitaly Kober
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7329)

Abstract

Correlation filters for object detection use information about the appearance and shape of the object of interest. Therefore, detection performance degrades when the appearance of the object in the scene differs from the appearance used in the filter design process. This problem has been approached by utilizing composite filters designed from a training set containing known views of the object of interest. However, common composite filter design is usually carried out under the assumption that the ideal appearance and shape of the target are known. In this work we propose an algorithm for composite filter design using noisy training images. The algorithm is a modification of the class synthetic discriminant function technique that uses arbitrary filter impulse responses. Furthermore, filters can be adapted to achieve a prescribed discrimination capability for a class of backgrounds if a representative sample is known. Computer simulation results obtained with the proposed algorithm are presented and compared with those of common composite correlation filters.

Keywords

correlation filters pattern recognition composite filters 

References

  1. 1.
    Javidi, B.: Real-Time Optical Information Processing. Academic Press, New York (1994)Google Scholar
  2. 2.
    Kumar, B.V.K.V., Mahalanobis, A., Juday, R.: Correlation pattern recognition. Cambridge Univ. Press, New York (2005)zbMATHCrossRefGoogle Scholar
  3. 3.
    Réfrégier, P., Goudail, F.: Statistical Image Processing Techniques for Noisy Images: An Application-Oriented Approach. Kluwer Academic Publishers, New York (2003)Google Scholar
  4. 4.
    Yaroslavsky, L.P.: The theory of optimal methods for localization of objects in pictures. In: Wolf, E. (ed.) Progress in Optics, pp. 145–201. Elsevier, Amsterdam (1993)Google Scholar
  5. 5.
    Kober, V., Campos, J.: Accuracy of location measurement of a noisy target in a nonoverlapping background. Journal of the Optical Society of America A 13(8), 1653–1666 (1996)CrossRefGoogle Scholar
  6. 6.
    Kumar, B.V.K.V., Dickey, F.M., DeLaurentis, J.M.: Correlation filters minimizing peak location errors. Journal of the Optical Society of America A 9(5), 678–682 (1992)CrossRefGoogle Scholar
  7. 7.
    VanderLugt, A.: Signal detection by complex spatial filtering. IEEE Transactions on Information Theory 10(2), 139–145 (1964)CrossRefGoogle Scholar
  8. 8.
    Javidi, B., Wang, J.: Design of filters to detect a noisy target in nonoverlapping background noise. Journal of the Optical Society of America A 11(10), 2604–2612 (1994)CrossRefGoogle Scholar
  9. 9.
    Aguilar-González, P.M., Kober, V.: Design of correlation filters for pattern recognition with disjoint reference image. Optical Engineering 50, 117201 (2011)CrossRefGoogle Scholar
  10. 10.
    Aguilar-González, P.M., Kober, V.: Design of correlation filters for pattern recognition using a noisy reference. Optics Communications 285(5), 574–583 (2012)CrossRefGoogle Scholar
  11. 11.
    Kumar, B.V.K.V.: Tutorial survey of composite filter designs for optical correlators. Applied Optics 31(23), 4773–4801 (1992)CrossRefGoogle Scholar
  12. 12.
    Kerekes, R.A., Kumar, B.V.K.V.: Selecting a composite correlation filter design: a survey and comparative study. Optical Engineering 47(6), 067202.1–067202.18 (2008)Google Scholar
  13. 13.
    Casasent, D.: Unified synthetic discriminant function computational formulation. Applied Optics 23(10), 1620–1627 (1984)CrossRefGoogle Scholar
  14. 14.
    Mahalanobis, A., Kumar, B.V.K.V., Casasent, D.: Minimum average correlation energy filters. Applied Optics 26(17), 3633–3640 (1987)CrossRefGoogle Scholar
  15. 15.
    Mahalanobis, A., Kumar, B.V.K.V., Song, S., Sims, S.R.F., Epperson, J.F.: Unconstrained correlation filters. Applied Optics 33(17), 3751–3759 (1994)CrossRefGoogle Scholar
  16. 16.
    Díaz-Ramírez, V.H., Kober, V.: Adaptive phase-input joint transform correlator. Applied Optics 46(26), 6543–6551 (2007)CrossRefGoogle Scholar
  17. 17.
    Díaz-Ramírez, V.H., Kober, V., Álvarez-Borrego, J.: Pattern recognition with an adaptive joint transform correlator. Applied Optics 45(23), 5929–5941 (2006)CrossRefGoogle Scholar
  18. 18.
    González-Fraga, J., Kober, V., Álvarez-Borrego, J.: Adaptive synthetic discriminant function filters for pattern recognition. Optical Engineering 45, 057005.1–057005.10 (2006)Google Scholar
  19. 19.
    Ramos-Michel, E.M., Kober, V.: Design of correlation filters for recognition of linearly distorted objects in linearly degraded scenes. Journal of the Optical Society of America. A 24(11), 3403–3417 (2007)CrossRefGoogle Scholar
  20. 20.
    Ramos-Michel, E.M., Kober, V.: Adaptive composite filters for pattern recognition in linearly degraded and noisy scenes. Optical Engineering 47(4), 047204.1–047204.7 (2008)Google Scholar
  21. 21.
    Yaroslavsky, L.P.: The theory of optimal methods for localization of objects in pictures. In: Wolf, E. (ed.) Progress in Optics, pp. 145–201. Elsevier (1993)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Pablo M. Aguilar-González
    • 1
  • Vitaly Kober
    • 1
  1. 1.Department of Computer ScienceCentro de Investigación Científica y de Educación, Superior de EnsenadaEnsenadaMéxico

Personalised recommendations