Prototyping structural descriptions: An inductive learning approach

  • L. P. Cordella
  • P. Foggia
  • R. Genna
  • M. Vento
Learning Methodologies
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1451)


In structural pattern recognition, a common problem is the difficulty of constructing classification models or rules from a set of examples. This paper illustrates a method for generating class descriptions from a training set by using inductive logic programming, and in particular an inductive learning algorithm based on the FOIL system. The goal of the method is to find descriptions which are general, i.e. are successfully applicable to recognize objects different from the ones in the training set, while preserving their discrimination ability. The application of the method to a difficult real-world problem (handprinted character recognition) is presented, proposing a hierarchical description and classification scheme in order to reduce the complexity of the task to a level which can be profitably handled by this kind of learning methodologies.


Structural Description Prototyping Inductive Learning FOIL 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pavlidis, T: Structural Pattern Recognition. Springer-Verlag (1977)Google Scholar
  2. 2.
    Eshera, M. A., Fu, K.S.: An image understanding system using attributed symbolic representation and inexact graph matching. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. PAMI-8, n. 5 (1986) 604–617Google Scholar
  3. 3.
    Rocha, J., Pavlidis, T.: A shape analysis model with applications to a character recognition system. IEEE Trams. Pattern Analysis and Machine Intelligence, Vol. PAMI-16, n. 4 (1994) 393–404CrossRefGoogle Scholar
  4. 4.
    Hsu, J., Hwang, S.: A machine learning approach for acquiring descriptive classification rules of shape contours. Pattern Recognition, Vol. 30, n. 2, pp. 245–252, (1997)CrossRefGoogle Scholar
  5. 5.
    Muggleton, S.: Inductive Logic Programming. New Generation Computing, Vol. 8, n. 4 (1991) 295–318Google Scholar
  6. 6.
    Quinlan, J.R.: Learning logical definitions from relations. Machine Learning, Vol. 5, n. 3 (1990) 239–266Google Scholar
  7. 7.
    Cordella, L.P., Foggia, P., Sansone, C., Vento, M.: Hierarchical description and recognition of linear shapes. Proc. 3rd International Workshop on Visual Forms (1997)Google Scholar
  8. 8.
    Boccignone, G., Chianese, A., Cordella, L.P., Marcelli, A.: Using skeletons for OCR. In: Progress in Image Analysis and Processing, World Scientific Publ. (1990)Google Scholar
  9. 9.
    Chianese, A., Cordella, L.P., De Santo, M., Vento, M.: Decomposition of ribbon-like shapes. Proc. 6th Scandinavian Conference on lmage Analysis. Oulu, Finland (1989) 416–423Google Scholar
  10. 10.
    ETL Database distributed by Electrotechnical Laboratory-Japanese Technical Corrunittee for OCR, during the 2nd ICDAR (1993)Google Scholar
  11. 11.
    Lavrac, N., Dzeroski, S.: Inductive Logic Programming: Techniques and Applications. Ellis Horwood (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • L. P. Cordella
    • 1
  • P. Foggia
    • 1
  • R. Genna
    • 1
  • M. Vento
    • 1
  1. 1.Dipartimento di Informatica e SistemisticaNapoliItaly

Personalised recommendations