Advertisement

Quantum Interference and Shape Detection

  • Davi Geiger
  • Zvi M. KedemEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10746)

Abstract

We address the problem of shape detection in settings where large shape deformations and occlusions occur with clutter noise present. We propose a quantum model for shapes by applying the quantum path integral formulation to an existing energy model for shapes (a Bayesian-derived cost function). We show that the classical statistical method derived from the quantum method, via the Wick rotation technique, is a voting scheme similar to the Hough transform. The quantum phenomenon of interference drives the quantum method for shape detection to excel, compared to the corresponding classical statistical method or the statistical Bayesian (energy optimization) method. To empirically demonstrate our approach, we focus on simple shapes: circles and ellipses.

Keywords

Shape Hough transform Interference Statistical methods Energy minimization Wick rotation 

Notes

Acknowledgments

The first author thanks the National Science Foundation for the Award Number 1422021, which partially supported this research. Both authors wish to thank Dan Pinkel for numerous interesting conversations about these ideas and methods and the anonymous reviewers for valued feedback.

References

  1. 1.
    Feynman, R., Hibbs, A.: Quantum Mechanics and Path Integrals: Emended by D. F. Steyer. Dover Publications, New York (2012)zbMATHGoogle Scholar
  2. 2.
    Feynman, R.: The Feynman Lectures on Physics, vol. 3. Addison Wesley, Boston (1971)Google Scholar
  3. 3.
    Wick, G.C.: Properties of Bethe-Salpeter wave functions. Phys. Rev. 96, 1124–1134 (1954)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Hough, P.V.C.: Machine analysis of bubble chamber pictures. In: 2nd International Conference on High-Energy Accelerators and Instrumentation, Proceedings Geneva, Switzerland, pp. 554–558 (1959)Google Scholar
  5. 5.
    Yuille, A.L.: Energy functions for early vision and analog networks. Biol. Cybern. 61(2), 115–123 (1989)CrossRefGoogle Scholar
  6. 6.
    Emms, D., Wilson, R., Hancock, E.: Graph matching using the interference of continuous-time quantum walks. Pattern Recogn. 42, 985–1002 (2009)CrossRefzbMATHGoogle Scholar
  7. 7.
    Emms, D., Wilson, R., Hancock, E.: Graph matching using the interference of discrete-time quantum walks. Image Vis. Comput. 27, 934–949 (2009)CrossRefzbMATHGoogle Scholar
  8. 8.
    Rangarajan, A., Gurumoorthy, K.S.: A Schrödinger wave equation approach to the eikonal equation: application to image analysis. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds.) EMMCVPR 2009. LNCS, vol. 5681, pp. 140–153. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-03641-5_11 CrossRefGoogle Scholar
  9. 9.
    Gurumoorthy, K.S., Rangarajan, A., Banerjee, A.: The complex wave representation of distance transforms. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 413–427. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-23094-3_30 Google Scholar
  10. 10.
    Cicconet, M., Geiger, D., Werman, M.: Complex-valued Hough transforms for circles. In: Proceedings, 2015 IEEE International Conference on Image Processing (ICIP), pp. 2801–2804, September 2015Google Scholar
  11. 11.
    Witkin, A.P.: Scale-space filtering. In: Proceedings of the Eighth International Joint Conference on Artificial Intelligence, pp. 1019–1022 (1983)Google Scholar
  12. 12.
    Lindeberg, T.: Scale-space theory: a basic tool for analysing structures at different scales. J. Appl. Stat. 2(21), 224–270 (1994). (Supplement on Advances in Applied Statistics: Statistics and Images: 2)Google Scholar
  13. 13.
    Siddiqi, K., Kimia, B.B.: A shock grammar for recognition. In: Computer Vision and Pattern Recognition, Proceedings CVPR 1996 (1996)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Science, Courant Institute of Mathematical SciencesNew York UniversityNew YorkUSA

Personalised recommendations