Multi-class Binary Symbol Classification with Circular Blurred Shape Models

  • Sergio Escalera
  • Alicia Fornés
  • Oriol Pujol
  • Petia Radeva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)


Multi-class binary symbol classification requires the use of rich descriptors and robust classifiers. Shape representation is a difficult task because of several symbol distortions, such as occlusions, elastic deformations, gaps or noise. In this paper, we present the Circular Blurred Shape Model descriptor. This descriptor encodes the arrangement information of object parts in a correlogram structure. A prior blurring degree defines the level of distortion allowed to the symbol. Moreover, we learn the new feature space using a set of Adaboost classifiers, which are combined in the Error-Correcting Output Codes framework to deal with the multi-class categorization problem. The presented work has been validated over different multi-class data sets, and compared to the state-of-the-art descriptors, showing significant performance improvements.


Shape Descriptor Zernike Moment Object Part Sift Descriptor Output Code 
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.
  2. 2.
    Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognition 37(1), 1–19 (2004)CrossRefGoogle Scholar
  3. 3.
    Khotanzad, A., Hong, Y.H.: Invariant image recognition by Zernike moments. PAMI 12(5), 489–497 (1990)CrossRefGoogle Scholar
  4. 4.
    Manjunath, B.S., Salembier, P., Sikora, T.: Introduction to MPEG-7: Multimedia Content Description Interface. Wiley, Chichester (2002)Google Scholar
  5. 5.
    Mokhtarian, F., Mackworth, A.K.: Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes. PAMI 8(1), 34–43 (1986)CrossRefGoogle Scholar
  6. 6.
    Belongie, S., Malik, J., Puzicha, J.: Shape Matching and Object Recognition Using Shape Contexts. PAMI, 509–522 (2002)Google Scholar
  7. 7.
    Bunke, H.: Attributed programmed graph grammars and their application to schematic diagram interpretation. PAMI 4(6), 574–582 (1982)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lladós, J., Martí, E., Villanueva, J.: Symbol Rec. by Error-Tolerant Subgraph Matching between Adjacency Graphs. PAMI 23(10), 1137–1143 (2001)CrossRefGoogle Scholar
  9. 9.
    Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Annals of Statistics 28(2), 337–374 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Dietterich, T.G., Bakiri, G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. JAIR 2, 263–286 (1995)zbMATHGoogle Scholar
  11. 11.
    Fornés, A., Escalera, S., Lladós, J., Sánchez, G., Radeva, P.I., Pujol, O.: Handwritten symbol recognition by a boosted blurred shape model with error correction. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds.) IbPRIA 2007. LNCS, vol. 4477, pp. 13–21. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Dietterich, T., Kong, E.: Error-correcting output codes corrects bias and variance. In: Prieditis, S., Russell, S. (eds.) ICML, pp. 313–321 (1995)Google Scholar
  13. 13.
    Dietterich, T., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. JAIR 2, 263–286 (1995)zbMATHGoogle Scholar
  14. 14.
    Pujol, O., Radeva, P., Vitrià, J.: DECOC: A heuristic method for application dependent design of ECOC. PAMI 28, 1001–1007 (2006)CrossRefGoogle Scholar
  15. 15.
    Escalera, S., Tax, D.M.J., Pujol, O., Radeva, P., Duin, R.P.W.: Subclass Problem-Dependent Design for Error-Correcting Output Codes. PAMI 30(6), 1041–1054 (2008)CrossRefGoogle Scholar
  16. 16.
    Allwein, E., Schapire, R., Singer, Y.: Reducing multiclass to binary: A unifying approach for margin classifiers. JMLR 1, 113–141 (2002)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Escalera, S., Pujol, O., Radeva, P.: On the Decoding Process in Ternary Error-Correcting Output Codes. PAMI (2009)Google Scholar
  18. 18.
    Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. JCV 60(2), 91–110 (2004)Google Scholar
  19. 19.
    Kim, W.Y., Kim, Y.S.: A new region-based shape descriptor. Hanyang University and Konan Technology (1999)Google Scholar
  20. 20.
    Standard MPEG ISO/IEC 15938-5:2003(E)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sergio Escalera
    • 1
    • 2
  • Alicia Fornés
    • 1
    • 3
  • Oriol Pujol
    • 1
    • 2
  • Petia Radeva
    • 1
    • 2
  1. 1.Computer Vision CenterBellaterraSpain
  2. 2.Dept. Matemàtica Aplicada i AnàlisiUBBarcelonaSpain
  3. 3.Dept. Computer ScienceBellaterraSpain

Personalised recommendations