A Novel Framework for Object Recognition under Severe Occlusion

  • Stamatia Giannarou
  • Tania Stathaki
Part of the Studies in Computational Intelligence book series (SCI, volume 410)


This work introduces a novel technique for the automatic identification of real world objects in complex scenes. The identification problem requires the comparison of assemblies of image regions with a previously stored view of a known prototype. Shape context representation and matching are employed for recovering point correspondences between the image and the prototype. Assuming that the prototype view is sufficiently similar in configuration with an object in the complex scene, the correspondence process will succeed. However, a number of ambient conditions such as partial object occlusion and contour distortion, may affect the performance of the matching process and consequently the identification result. A novel multistage type of clustering of suspicious image locations is applied in a novel fashion to enable the identification of regions of interest on the complex scene, based on a set of density and figural continuity metrics. In order to increase the robustness of the identifier to mismatches and reduce the computational cost of the process, a selection of the initial suspicious regions is applied. The performance of the identifier has been examined in a great range of complex image and prototype object selections.


Object Recognition Edge Point Complex Scene Contour Point Shape Context 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Machine Intell. 24(4), 509–522 (2002)CrossRefGoogle Scholar
  2. 2.
    Bezdek, J.C., Pal, M.R., Keller, J., Krisnapuram, R.: Fuzzy models and algorithms for pattern recognition and image processing. Kluwer Academic Publishers (1999)Google Scholar
  3. 3.
    Canny, J.F.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Machine Intell. 8(6), 679–698 (1986)CrossRefGoogle Scholar
  4. 4.
    Carter, J.R.: Boundary tracing method and system. European Patent Applcation EP341819-A3 (1989)Google Scholar
  5. 5.
    Chellappa, R., Bagdazian, R.: Fourier coding of image boundaries. IEEE Trans. Pattern Anal. Machine Intell. 6(1), 102–105 (1984)CrossRefGoogle Scholar
  6. 6.
    Chiu, S.: Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems 2(3) (1994)Google Scholar
  7. 7.
    Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities. Academic Press (1997)Google Scholar
  8. 8.
    Deriche, R., Cocquerez, J.P., Almouzny, G.: An efficient method to build early image description. In: 9th International Conference on Pattern Recognition, Rome (November 1988)Google Scholar
  9. 9.
    Haralick, R., Shapiro, L.G.: Computer and Robot Vision, vol. I, pp. 28–48. Addison-Wesley (1992)Google Scholar
  10. 10.
    Harris, C.J.: Tracking with rigid models. In: Blake, A., Yuille, A. (eds.) Active Vision, ch. 4, pp. 59–73. MIT Press, Cambridge (1992)Google Scholar
  11. 11.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory IT (8), 179–187 (1962)Google Scholar
  12. 12.
    Jonker, R., Volgenant, A.: A shortest augmenting path algorithm for dense and sparse linear assignment problems. Computing 38, 325–340 (1987)MathSciNetzbMATHCrossRefGoogle Scholar
  13. 13.
    Kauppinen, H., Seppanen, T., Pietikainen, M.: An experimental comparison of autoregressive and fourier-based descriptors in 2D shape classification. IEEE Trans. Pattern Anal. Machine Intell. 17(2), 201–207 (1995)CrossRefGoogle Scholar
  14. 14.
    Kopf, S., Haenselmann, T., Effelsberg, W.: Enhancing curvature scale space features for robust shape classification. In: Proceedings of IEEE International Conference on Multimedia and Expo. ICME 2005 (July 2005)Google Scholar
  15. 15.
    Latecki, L.J., Lakamper, R.: Shape similarity measure based on correspondence of visual parts. IEEE Trans. Pattern Anal. Machine Intell. 22(10), 1185–1190 (2000)CrossRefGoogle Scholar
  16. 16.
    Loncaric, S.: A survey of shape analysis techniques. Pattern Recognition 31(8), 983–1001 (1998)CrossRefGoogle Scholar
  17. 17.
    Lowe, D.: Integrated treatment of matching and measurement errors for robust model-based motion tracking. In: Proceedings IEEE 3rd International Conference on Computer Vision, pp. 436–440 (1990)Google Scholar
  18. 18.
    Lowe, D.: Distinctive image features from scale-invariant key-points. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  19. 19.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Machine Intell. 24(10), 1615–1630 (2005)CrossRefGoogle Scholar
  20. 20.
    Mokhtarian, F., Mackworth, A.: Scale-based description and recognition of planar curves and two-dimensional shapes. IEEE Trans. Pattern Anal. Machine Intell. 8(1), 34–43 (1986)CrossRefGoogle Scholar
  21. 21.
    Van Otterloo, P.J.: A contour-oriented approach to shape analysis. Prentice Hall International (UK) Ltd. (1991)Google Scholar
  22. 22.
    Rattarangsi, A., Chin, R.T.: Scale-based detection of corners of planar curves. IEEE Trans. Pattern Anal. Machine Intell. 14(4), 430–449 (1992)CrossRefGoogle Scholar
  23. 23.
    Ross, T.J.: Fuzzy logic with engineering applications. Publishing House of Electronics Industry, Beijing (2004)zbMATHGoogle Scholar
  24. 24.
    Di Ruberto, C., Morgera, A.: A comparison of 2-D moment-based description techniques. In: International Conference on Image Analysis and Processing, pp. 212–219 (2005)Google Scholar
  25. 25.
    Taubin, G., Cooper, D.B.: Geometric invariance in computer vision. MIT Press (1992)Google Scholar
  26. 26.
    Teague, M.R.: Image analysis via the general theory of moments. Journal of the Optical Society of America 70(8), 920–930 (1980)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Terzopoulos, D., Witkin, A., Kass, M.: Constraints on deformable models: recovering 3d shape and nongrid motion. Artificial Intelligence 36(1), 91–123 (1988)zbMATHCrossRefGoogle Scholar
  28. 28.
    Veltkamp, R.C., Hagedoorn, M.: State of the art in shape matching. Principles of Visual Information Retrieval, 87–119 (2001)Google Scholar
  29. 29.
    Yager, R., Filev, D.: Generation of fuzzy rules by mountain clustering. Journal of Intelligent and Fuzzy Systems 2(3), 209–219 (1994)Google Scholar
  30. 30.
    Zhang, D., Lu, G.: Enhanced generic fourier descriptors for object-based image retrieval. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 4, pp. 3668–3671 (2002)Google Scholar
  31. 31.
    Zhang, D., Lu, G.: Shape based image retrieval using generic fourier descriptors. Signal Processing: Image Communication 17(10), 825–848 (2002)CrossRefGoogle Scholar
  32. 32.
    Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognition 37(1), 1–19 (2004)zbMATHCrossRefGoogle Scholar
  33. 33.
    Zhong, Y., Jain, A.K., Dubuisson-Jolly, M.P.: Object tracking using deformable templates. IEEE Trans. Pattern Anal. Machine Intell. 22(5), 544–549 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2013

Authors and Affiliations

  • Stamatia Giannarou
    • 1
  • Tania Stathaki
    • 1
  1. 1.Imperial College LondonLondonUK

Personalised recommendations