Region Based Visual Object Categorization Using Segment Features and Polynomial Modeling

  • Huanzhang Fu
  • Alain Pujol
  • Emmanuel Dellandréa
  • Liming Chen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5342)


This paper presents a novel approach for visual object classification. Based on Gestalt theory, we propose to extract features from coarse regions carrying visually significant information such as line segments and/or color and to include neighborhood information in them. We also introduce a new classification method based on the polynomial modeling of feature distribution which avoids some drawbacks of a popular approach, namely “bag of keypoints”. Moreover we show that by separating features extracted from different sources in different “channels”, which are then combined using a late fusion strategy, we can limit the impact of feature dimensionality and actually improve classification accuracy. Using this classifier, experiments reveal that our features lead to better results than the popular SIFT descriptors, but also that they can be combined with SIFT features to reinforce performance, suggesting that our features managed to extract information which is complementary to the one of SIFT features.


Feature Vector Gaussian Mixture Model Fusion Strategy Visual Content Sift Feature 
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.
    The PASCAL Visual Object Classes Challenge 2007 Results (2007),
  2. 2.
    Dance, C., Willamowski, J., Fan, L., Bray, C., Csurka, G.: Visual categorization with bags of keypoints. In: ECCV International Workshop on Statistical Learning in Computer Vision (2004)Google Scholar
  3. 3.
    Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: Object modeling and recognition using local affine-invariant image descriptors and multi-view spatial contraints. International Journal of Computer Vision 66(3) (2006)Google Scholar
  4. 4.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  5. 5.
    Lindeberg, T.: Feature detection with automatic scale selection. International Journal of Computer Vision 30(2), 79–116 (1998)CrossRefGoogle Scholar
  6. 6.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)CrossRefGoogle Scholar
  7. 7.
    Li, F.F., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), pp. 524–531 (2005)Google Scholar
  8. 8.
    Kaniza, G.: Grammatica del vedere. Il Mulino (1997)Google Scholar
  9. 9.
    Wertheirmer, M.: Untersuchungen zur lehre der gestalt ii. Psychologische Forschung 4, 301–350 (1923)CrossRefGoogle Scholar
  10. 10.
    Desolneux, A., Moisan, L., Morel, J.: From Gestalt Theory to Image Analysis: A Probabilistic Approach. Springer, Heidelberg (2008)CrossRefzbMATHGoogle Scholar
  11. 11.
    Pujol, A., Chen, L.: Coarse adaptive color image segmentation for visual object classification. In: Proceedings of the 15th International Conference on Systems, Signals and Image Processing (2008)Google Scholar
  12. 12.
    Martinetz, T., Schulten, K.: A “neural-gas” network learns topologies. Artificial Neural Networks I, 397–402 (1991)Google Scholar
  13. 13.
    Zhu, S.C., Yuille, A.: Region competition: Unifying snakes, region growing, and bayes/mdl for multiband image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(9), 884–900 (1996)CrossRefGoogle Scholar
  14. 14.
    Stricker, M.A., Orengo, M.: Similarity of color images. In: Storage and Retrieval for Image and Video Databases (SPIE), pp. 381–392 (1995)Google Scholar
  15. 15.
    Trémeau, A., Fernandez-Maloigne, C., Bonton, P.: Digital Color Imaging - From acquisition to Processing. Dunod (in French) (January 2004)Google Scholar
  16. 16.
    Deng, Y., Manjunath, B., Kenney, C., Moore, M., Shin, H.: An efficient color representation for image retrieval. IEEE Transactions on Image Processing 10(1), 140–147 (2001)CrossRefzbMATHGoogle Scholar
  17. 17.
    Ardabilian, M., Chen, L.: A new line extraction algorithm: Fast connective hough transform. In: Proceedings of PRIP 2001, p. 127 (2001)Google Scholar
  18. 18.
    Bellman, R.: Adaptive Control Processes: A Guided Tour. Princeton University Press, Princeton (1961)CrossRefzbMATHGoogle Scholar
  19. 19.
    Saeys, Y., Inza, I., Larranaga, P.: A review of feature selection techniques in bioinformatics. Oxford University Press, Oxford (2007)Google Scholar
  20. 20.
    Fisher, R.A.: The use of multiple measurements in taxonomic problems. Annals of Eugenics 7, 179–188 (1936)CrossRefGoogle Scholar
  21. 21.
    Snoek, C.G.M., Worring, M., Smeulders, A.W.M.: Early versus late fusion in semantic video analysis. In: MULTIMEDIA 2005: Proceedings of the 13th annual ACM international conference on Multimedia, pp. 399–402. ACM, New York (2005)Google Scholar
  22. 22.
    Freund, Y., Schapire, R.: A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14(5), 771–780 (1999)Google Scholar
  23. 23.
    Nowozin, S.: Libsift - scale-invariant feature transform implementation (2005),

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Huanzhang Fu
    • 1
  • Alain Pujol
    • 1
  • Emmanuel Dellandréa
    • 1
  • Liming Chen
    • 1
  1. 1.LIRIS, UMR 5205 CNRSEcole Centrale de LyonEcully CedexFrance

Personalised recommendations