Multi-class Binary Object Categorization Using Blurred Shape Models

  • Sergio Escalera
  • Alicia Fornès
  • Oriol Pujol
  • Josep Lladós
  • Petia Radeva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

The main difficulty in the binary object classification field lays in dealing with a high variability of symbol appearance. Rotation, partial occlusions, elastic deformations, or intra-class and inter-class variabilities are just a few problems. In this paper, we introduce a novel object description for this type of symbols. The shape of the object is aligned based on principal components to make the recognition invariant to rotation and reflection. We propose the Blurred Shape Model (BSM) to describe the binary objects. This descriptor encodes the probability of appearance of the pixels that outline the object’s shape. Besides, we present the use of this descriptor in a system to improve the BSM performance and deal with binary objects multi-classification problems. Adaboost is used to train the binary classifiers, learning the BSM features that better split object classes. Then, the different binary problems learned by the Adaboost are embedded in the Error Correcting Output Codes framework (ECOC) to deal with the muti-class case. The methodology is evaluated in a wide set of object classes from the MPEG07 repository. Different state-of-the-art descriptors are compared, showing the robustness and better performance of the proposed scheme when classifying objects with high variability of appearance.

Keywords

Shape descriptors Multi-class classification Adaboost Error Correcting Output Codes 

References

  1. 1.
    Torralba, A., Murphy, K., Freeman, W.: Sharing visual features for multiclass and multiview object detection, Technical Report, Massachusetts Institute of Technology Computer Science and Artificial Intelligence (MIT AIM) (2004)Google Scholar
  2. 2.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. The Annals of Statistics 8(2), 337–374 (1998)MathSciNetGoogle Scholar
  3. 3.
    Pujol, O., Radeva, P., Vitrià, J.: Discriminant ECOC: a heuristic method for application dependent design of error correcting output codes. IEEE Transaction on Pattern Analysis and Machine Intelligence 28, 1007–1012 (2006)CrossRefGoogle Scholar
  4. 4.
  5. 5.
    Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognition 37, 1–19 (2004)MATHCrossRefGoogle Scholar
  6. 6.
    Kim, W.: A new region-based shape descriptor, Technical report, Hanyang University and Konan Technology (1999)Google Scholar
  7. 7.
    ISO/IEC 15938-5:2003(E)Google Scholar
  8. 8.
    Lladós, J., Valveny, E., Sánchez, G., Martí, E.: Symbol Recognition: Current Advances and Perspectives. In: Blostein, D., Kwon, Y.-B. (eds.) GREC 2001. LNCS, vol. 2390, pp. 104–127. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Manjunath, B., Salembier, P., Sikora, T.: Introduction to mpeg-7, Multimedia content description interface. John Wiley and Sons, Chichester (2002)Google Scholar
  10. 10.
    Escalera, S., Pujol, O., Radeva, P.: Decoding of Ternary Error Correcting Output Codes. In: Martínez-Trinidad, J.F., Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Dietterich, T., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Artificial Intelligence Research 2, 263–286 (1995)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Sergio Escalera
    • 1
    • 2
  • Alicia Fornès
    • 1
    • 3
  • Oriol Pujol
    • 1
    • 2
  • Josep Lladós
    • 1
    • 3
  • Petia Radeva
    • 1
    • 2
  1. 1.Computer Vision Center, Universitat Autònoma de Barcelona, Campus UAB, Edifici O, 08193, BellaterraSpain
  2. 2.Dept. Matemàtica Aplicada i Anàlisi, Universitat de Barcelona, Gran Via 585, 08007, BarcelonaSpain
  3. 3.Dept. Ciències de la Computació, Universitat Autònoma de Barcelona, Campus UAB, Edifici Q, 08193, BellaterraSpain

Personalised recommendations