Skip to main content
SpringerLink
Log in

A robust object category detection system using deformable shapes

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

An object can often be uniquely identified by its shape, which is usually fairly invariant. However, when the search is for a type of object or an object category, there can be variations in object deformation (i.e. variations in body shapes) and articulation (i.e. joint movement by limbs) that complicate their detection. We present a system that can account for this articulation variation to improve the robustness of its object detection by using deformable shapes as its main search criteria. However, existing search techniques based on deformable shapes suffer from slow search times and poor best matches when images are cluttered and the search is not initialised. To overcome these drawbacks, our object detection system uses flexible shape templates that are augmented by salient object features and user-defined heuristics. Our approach reduces computation time by prioritising the search around these salient features and uses the template heuristics to find truer positive matches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Bern, M.W., Eppstein, D.: Mesh generation and optimal triangulation. In: Du, D.Z., Hwang, F.K.M. (eds.) Computing in Euclidean Geometry, 2nd edn. Lecture Notes Series on Computing, vol. 4, pp. 47–123. World Scientific, Singapore (1995) http://www.ics.uci.edu/~eppstein/pubs/BerEpp-CEG-95.pdf

  2. Chang, T.L., Liu, T.L.: Detecting deformable objects with flexible shape priors. In: ICPR ’04: Proceedings of the Pattern Recognition, 17th International Conference on (ICPR’04), vol 4, pp. 155–158. IEEE Computer Society, Washington, DC (2004) Doi:10.1109/ICPR.2004.291

  3. Dia: (2006) http://www.gnome.org/projects/dia

  4. Felzenszwalb, P.F.: Representation and detection of deformable shapes. CVPR 1, 102–108 (2003) http://citeseer.ist.psu.edu/felzenszwalb03representation.html

  5. Felzenszwalb P.F. (2005). Representation and detection of deformable shapes. IEEE Trans. Pattern Anal. Mach. Intell. 27(2): 208–220 Doi:10.1109/TPAMI.2005.35

    Article  Google Scholar 

  6. Feraud R., Bernier O.J., Viallet J.E. and Collobert M. (2001). A fast and accurate face detector based on neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 23(1): 42–53 Doi:10.1109/34.899945

    Article  Google Scholar 

  7. GIMP: (2006) http://www.gimp.org

  8. Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comput. Vis. 1(4), 321–331 (1988) Doi:10.1007/BF00133570. http://dx.doi.org/10.1007/BF00133570

    Google Scholar 

  9. Ke, Y., Sukthankar, R.: Pca-sift: a more distinctive representation for local image descriptors. In: Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, vol. 2, pp. II–506–II–513, vol.2 (2004). Doi:10.1109/CVPR.2004.1315206

  10. Lamdan, Y., Schwartz, J., Wolfson, H.: Object recognition by affine invariant matching. In: Computer Vision and Pattern Recognition, 1988. Proceedings CVPR ’88., Computer Society Conference on, pp. 335–344 (1988) Doi:10.1109/CVPR.1988.196257

  11. Li, W.J., Lee, T.: Image registration and object recognition by affine invariant matching. In: Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on, pp. 56–59 (2001) Doi:10.1109/ISIMP.2001.925330

  12. Mohan A., Papageorgiou C. and PoggioT. (2001). Example-based object detection in images by components. IEEE Trans. Pattern Anal. Mach. Intell. 23(4): 349–361 Doi:10.1109/34.917571

    Article  Google Scholar 

  13. OpenCV: (2006) http://sourceforge.net/projects/opencv

  14. Osuna, E., Freund, R., Girosit, F.: Training support vector machines: an application to face detection. In: Computer Vision and Pattern Recognition, 1997. Proceedings, 1997 IEEE Computer Society Conference on, pp. 130–136 (1997) Doi:10.1109/CVPR.1997.609310

  15. Thuresson, J., Carlsson, S.: Finding object categories in cluttered images using minimal shape prototypes. In: SCIA, pp. 1122–1129 (2003)

  16. Verschae R. and del Solar J.R. (2003). A Hybrid Face Detector Based on an Asymmetrical Adaboost Cascade Detector and a Wavelet-Bayesian-Detector. Springer, Berlin

    Google Scholar 

  17. Viola P. and Jones M.J. (2004). Robust real-time face detection. Int. J. Comput. Vision 57(2): 137–154 Doi:10.1023/B:VISI.0000013087.49260.fb

    Article  Google Scholar 

  18. Xiao, R., Zhu, L., Zhang, H.J.: Boosting chain learning for object detection.In: Computer Vision, 2003. Proceedings. 9th IEEE International Conference on, vol. 1, pp. 709–715 (2003). Doi:10.1109/ICCV.2003.1238417

  19. Yezzi A.J., Kichenassamy S., Kumar A., Olver P. and Tannenbaum A. (1997). A geometric snake model for segmentation of medical imagery. Med. Imaging, IEEE Trans. 16(2): 199–209. Doi:10.1109/42.563665

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Queensland University of Technology, 126 Margaret St, Brisbane, Australia

    Robert Smith & Binh Pham

Authors
  1. Robert Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Binh Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Robert Smith.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Smith, R., Pham, B. A robust object category detection system using deformable shapes. Machine Vision and Applications 20, 119–130 (2009). https://doi.org/10.1007/s00138-007-0112-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-007-0112-0

Keywords

Search

Navigation