Advertisement

A Linear Programming Based Method for Joint Object Region Matching and Labeling

  • Junyan Wang
  • Li Wang
  • Kap Luk Chan
  • Martin Constable
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7725)

Abstract

Object matching can be achieved by finding the superpixels matched across the image and the object template. It can therefore be used for detecting or labeling the object region. However, the matched superpixels are often sparsely distributed within the image domain, and there could therefore be a significant proportion of incorrectly detected or labeled regions even though there are few outlier matches. Consequently, the labeled regions may be unreliable for locating, extracting or representing the object. To address these problems, we propose to impose label priors that were previously incorporated in segmentation on the object matching. Specifically, in order to label as many regions as possible on the object, we propose to adopt the boundary-weighted smoothness prior. To reduce the singular outlier matches as much as possible, we propose to adopt the minimum description length principle adopted in segmentation. We then linearize the priors and incorporate them in the linear programming (LP) formulation of matching. The above gives rise to a novel general LP model for joint object region matching and labeling. This work extends the scope of conventional LP based object matching. The experimental results show that our method compares favorably to the LP based matching methods for object region labeling on a challenging dataset.

Keywords

Feature Match Object Region Linear Programming Formulation Region Label Convex Quadratic Programming 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. TPAMI 24, 509–522 (2002)CrossRefGoogle Scholar
  2. 2.
    Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondences. In: CVPR (2005)Google Scholar
  3. 3.
    Torresani, L., Kolmogorov, V., Rother, C.: Feature Correspondence Via Graph Matching: Models and Global Optimization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 596–609. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  4. 4.
    Jiang, H., Drew, M.S., Li, Z.N.: Convex quadratic programming for object localization. In: ICPR (2006)Google Scholar
  5. 5.
    Jiang, H., Yu, S.: Linear solution to scale and rotation invariant object matching. In: CVPR (2009)Google Scholar
  6. 6.
    Li, H., Kim, E., Huang, X., He, L.: Object matching with a locally affine-invariant constraint. In: CVPR (2010)Google Scholar
  7. 7.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI 23, 1222–1239 (2001)CrossRefGoogle Scholar
  8. 8.
    Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. TPAMI 18, 884–900 (1996)CrossRefGoogle Scholar
  9. 9.
    Ferrari, V., Tuytelaars, T., Gool, L.: Simultaneous object recognition and segmentation from single or multiple model views. IJCV 67, 159–188 (2006)CrossRefGoogle Scholar
  10. 10.
    Kim, T.H., Lee, K.M., Lee, S.U.: A unified probabilistic approach to feature matching and object segmentation. In: ICPR (2010)Google Scholar
  11. 11.
    Jiang, H., Drew, M.S., Li, Z.N.: Matching by linear programming and successive convexification. TPAMI 29, 959–975 (2007)CrossRefGoogle Scholar
  12. 12.
    Jiang, H.: Finding Human Poses in Videos Using Concurrent Matching and Segmentation. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part I. LNCS, vol. 6492, pp. 228–243. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Toshev, A., Taskar, B., Daniilidis, K.: Shape-based object detection via boundary structure segmentation. IJCV 99, 123–146 (2012)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Jiang, H., Tian, T.P., Sclaroff, S.: Scale and rotation invariant matching using linearly augmented trees. In: CVPR (2011)Google Scholar
  15. 15.
    Li, H., Huang, J., Zhang, S., Huang, X.: Optimal object matching via convexification and composition. In: ICCV (2011)Google Scholar
  16. 16.
    Jiang, H., Tian, T.P., He, K., Sclaroff, S.: Scale resilient, rotation invariant articulated object matching. In: CVPR (2012)Google Scholar
  17. 17.
    Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: Turbopixels: Fast superpixels using geometric flows. TPAMI 31, 2290–2297 (2009)CrossRefGoogle Scholar
  18. 18.
    Li, S.Z.: Markov random field modeling in image analysis, 3rd edn. Springer-Verlag New York, Inc. (2009)Google Scholar
  19. 19.
    Kolmogorov, V., Zabih, R.: What Energy Functions Can Be Minimizedvia Graph Cuts? TPAMI 26, 147–159 (2004)CrossRefGoogle Scholar
  20. 20.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contour. IJCV 22, 61–79 (1997)zbMATHCrossRefGoogle Scholar
  21. 21.
    Pardalos, P.M., Vavasis, S.A.: Quadratic programming with one negative eigenvalue is NP-hard. Journal of Global Optimization 1, 15–22 (1991)MathSciNetzbMATHCrossRefGoogle Scholar
  22. 22.
    Vazirani, V.V.: Approximation algorithms. Springer (2001)Google Scholar
  23. 23.
    Gangbo, W., McCann, R.J.: Shape recognition via wasserstein distance. Quarterly of Applied Mathematics LVIII, 705–737 (2000)MathSciNetGoogle Scholar
  24. 24.
    Ni, K., Bresson, X., Chan, T.F., Esedoglu, S.: Local histogram based segmentation using the wasserstein distance. IJCV 84, 97–111 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Junyan Wang
    • 1
  • Li Wang
    • 2
  • Kap Luk Chan
    • 2
  • Martin Constable
    • 1
  1. 1.School of Art, Design and MediaNanyang Technological UniversitySingapore
  2. 2.School of Electrical and Electronic EngineeringNanyang Technological UniversitySingapore

Personalised recommendations