Object Recognition Using Junctions

  • Bo Wang
  • Xiang Bai
  • Xinggang Wang
  • Wenyu Liu
  • Zhuowen Tu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6315)


In this paper, we propose an object detection/recognition algorithm based on a new set of shape-driven features and morphological operators. Each object class is modeled by the corner points (junctions) on its contour. We design two types of shape-context like features between the corner points, which are efficient to compute and effective in capturing the underlying shape deformation. In the testing stage, we use a recently proposed junction detection algorithm [1] to detect corner points/junctions on natural images. The detection and recognition of an object are then done by matching learned shape features to those in the input image with an efficient search strategy. The proposed system is robust to a certain degree of scale change and we obtained encouraging results on the ETHZ dataset. Our algorithm also has advantages of recognizing object parts and dealing with occlusions.


Object Recognition Object Detection Corner Point Junction Point Shape Match 
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.


  1. 1.
    Maire, M., Arbelaez, P., Fowlkes, C., Malik, J.: Using contour to detect and localize junctions in natural images. In: CVPR (2008)Google Scholar
  2. 2.
    Viola, P.A., Jones, M.J.: Robust real-time face detection. IJCV 57, 137–154 (2004)CrossRefGoogle Scholar
  3. 3.
    Kumar, S., Hebert, M.: Discriminative random fields: a discriminative framework for contextual interaction in classification. In: ICCV (2003)Google Scholar
  4. 4.
    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR (2008)Google Scholar
  5. 5.
    Dollár, P., Babenko, B., Belongie, S., Perona, P., Tu, Z.: Multiple component learning for object detection. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 211–224. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: CVPR (2009)Google Scholar
  7. 7.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  8. 8.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proc. of CVPR, pp. 886–893 (2005)Google Scholar
  9. 9.
    Gu, C., Lim, J.J., Arbelaez, P., Malik, J.: Recognition using regions. In: CVPR (2009)Google Scholar
  10. 10.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: Proc. of CVPR (2008)Google Scholar
  11. 11.
    Yuille, A.L., Hallinan, P.W., Cohen, D.S.: Feature extraction from faces using deformable templates. IJCV 8, 99–111 (1992)CrossRefGoogle Scholar
  12. 12.
    Ballard, D.H.: Generalizing the hough transform to detect arbitrary shapes. Pattern Recognition 13, 111–122 (1981)zbMATHCrossRefGoogle Scholar
  13. 13.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24, 509–522 (2002)Google Scholar
  14. 14.
    Grauman, K., Darrell, T.: The pyramid match kernel: Discriminative classification with sets of image features. In: Proc. of ICCV (2005)Google Scholar
  15. 15.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV 61, 55–79 (2005)CrossRefGoogle Scholar
  16. 16.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. PAMI 30, 36–51 (2008)Google Scholar
  17. 17.
    Opelt, A., Pinz, A., Zisserman, A.: A boundary-frament-model for object detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 575–588. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  18. 18.
    Gavrila, D.: A bayesian, exemplar-based approach to hierarchical shape matching. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1408–1421 (2007)CrossRefGoogle Scholar
  19. 19.
    Felzenszwalb, P.F., Schwartz, J.D.: Hierachical matching of deformable shapes. In: CVPR (2007)Google Scholar
  20. 20.
    Zhu, L., Chen, Y., Ye, X., Yuille, A.L.: Structure-perceptron learning of a hierarchical log-linear model. In: Proc. of CVPR (2008)Google Scholar
  21. 21.
    Marr, D.: Vision. W.H. Freeman and Co., San Francisco (1982)Google Scholar
  22. 22.
    Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, colour and texture cues. PAMI 26, 530–549 (2004)Google Scholar
  23. 23.
    Shotton, J., Blake, A., Cipolla, R.: Multi-scale categorical object recognition using contour fragments. PAMI 30, 1270–1281 (2008)Google Scholar
  24. 24.
    Heitz, G., Elidan, G., Parker, B., Koller, D.: Loops: Localizing object outlines using probabilistics shape. In: NIPS (2008)Google Scholar
  25. 25.
    Ferrari, V., Jurie, F., Schmid, C.: Accurate object detection combining recognition and segmentation. In: CVPR (2007)Google Scholar
  26. 26.
    Zhu, Q., Wang, L., Wu, Y., Shi, J.: Contour context selection for object detection: A set-to-set contour matching approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 774–787. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  27. 27.
    Lu, C., Latecki, L., Adluru, N., Yang, X., Ling, H.: Shape guided contour grouping with particle filters. In: ICCV (2009)Google Scholar
  28. 28.
    Trinh, N., Kimia, B.: Category-specific object recognition and segmentation using a skeletal shape model. In: BMVC (2009)Google Scholar
  29. 29.
    Kovesi, P.D.: MATLAB and Octave functions for computer vision and image processing. School of Computer Science & Software Engineering, The University of Western Australia (2008),
  30. 30.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: From images to shape models for object detection. Technical Report 6600, INRIA (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Bo Wang
    • 1
  • Xiang Bai
    • 1
  • Xinggang Wang
    • 1
  • Wenyu Liu
    • 1
  • Zhuowen Tu
    • 2
  1. 1.Dept. of Electronics and Information EngineeringHuazhong University of Science and TechnologyChina
  2. 2.Lab of Neuro ImagingUniversity of CaliforniaLos Angeles

Personalised recommendations