Incorporating Geometry Information with Weak Classifiers for Improved Generic Visual Categorization

  • Gabriela Csurka
  • Jutta Willamowski
  • Christopher R. Dance
  • Florent Perronnin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)

Abstract

In this paper, we improve the performance of a generic visual categorizer based on the ”bag of keypatches” approach using geometric information. More precisely, we consider a large number of simple geometrical relationships between interest points based on the scale, orientation or closeness. Each relationship leads to a weak classifier. The boosting approach is used to select from this multitude of classifiers (several millions in our case) and to combine them effectively with the original classifier. Results are shown on a new challenging 10 class dataset.

Keywords

Interest Point Image Patch Circular Patch Interest Point Detector Soft Margin 
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.

References

  1. 1.
    Carbonetto, P., de Freitas, N., Barnard, K.: A statistical model for general contextual object recognition. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3021, pp. 350–362. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Chen, Y., Wang, J.Z.: Image categorization by learning and reasoning with regions. JMLR 5, 913–939 (2004)Google Scholar
  3. 3.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. ECCV International Workshop on Statistical Learning in Computer Vision (2004)Google Scholar
  4. 4.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR, vol. 2, pp. 264–271 (2003)Google Scholar
  5. 5.
    Ferrari, V., Tuytelaars, T., Van Gool, L.: Simultaneous object recognition and segmentation by image exploration. In: Proc. ECCV, vol. 1, pp. 40–54 (2004)Google Scholar
  6. 6.
    Lazebnik, S., Schmid, C., Ponce, J.: Semi-local affine parts for object recognition. In: Proc. BMVC, vol. 2, pp. 959–968 (2004)Google Scholar
  7. 7.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Proc. ECCV Workshop on Statistical Learning in Computer Vision, pp. 17–32 (2004)Google Scholar
  8. 8.
    Li, Y., Bilmes, J.A., Shapiro, L.G.: Object class recognition using images of abstract regions. In: Proc. ICPR, vol. 1, pp. 40–44 (2004)Google Scholar
  9. 9.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. ICCV, pp. 1150–1157 (1999)Google Scholar
  10. 10.
    Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Proc. ECCV, vol. 1, pp. 128–142 (2002)Google Scholar
  11. 11.
    Opelt, A., Fussenegger, M., Pinz, A., Auer, P.: Weak hypotheses and boosting for generic object detection and recognition. In: Proc. ECCV, vol. 2, pp. 71–84 (2004)Google Scholar
  12. 12.
    Pan, J.-Y., Yang, H.-J., Faloutsos, C., Duygulu, P.: GCap: Graph-based automatic image captioning. In: Proc. CVPR Workshop on Multimedia Data and Document Engineering (2004)Google Scholar
  13. 13.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In: Advances in Large Margin Classifiers. MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Rätsch, G., Onoda, T., Müller, K.-R.: Soft margins for Adaboost. ML 42(3), 287–320 (2000)Google Scholar
  15. 15.
    Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)MATHCrossRefGoogle Scholar
  16. 16.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing features: Efficient boosting procedures for multiclass object detection. In: Proc. CVPR, vol. 2, pp. 762–769 (2004)Google Scholar
  17. 17.
    Vapnik, V.: Statistical Learning Theory. Wiley, Chichester (1998)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Gabriela Csurka
    • 1
  • Jutta Willamowski
    • 1
  • Christopher R. Dance
    • 1
  • Florent Perronnin
    • 1
  1. 1.Xerox Research Centre EuropeMeylanFrance

Personalised recommendations