Advertisement

Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features

  • Kyoung Min Kim
  • Joong Jo Park
  • Young Gi Song
  • In Cheol Kim
  • Ching Y. Suen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

Off-line handwritten numeral recognition is a very difficult task. It is hard to achieve high recognition results using a single set of features and a single classifier, since handwritten numerals contain many pattern variations which mostly depend upon individual writing styles. In this paper, we propose a recognition system using hybrid features and a combined classifier. To improve recognition rate, we select mutually beneficial features such as directional features, crossing point features and mesh features, and create three new hybrid feature sets from them. These feature sets hold the local and global characteristics of input numeral images. We also implement a combined classifier from three neural network classifiers to achieve a high recognition rate, using fuzzy integral for multiple network fusion. In order to verify the performance of the proposed recognition system, experiments with the unconstrained handwritten numeral database of Concordia University, Canada were performed, producing a recognition rate of 97.85%.

Keywords

Feature Vector Recognition Rate Feature Extraction Method Recognition Result Fuzzy Measure 
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.
    Jain, A.K., Taxt, T.: Feature Extraction Methods for Character Recognition -A Survey. Pattern Recognition 29(4), 641–662 (1996)CrossRefGoogle Scholar
  2. 2.
    Soo, R.G., Sung Il, C.: Recognition of Handwritten Numerals by Relearning Hidden Layer Outputs of Modular Neural Nertworks. Korea Information Science Society 23(9), 931–939 (1996)Google Scholar
  3. 3.
    Cho, S.B.: Neural network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Trans. on Neural Networks 8(1), 43–53 (1997)CrossRefGoogle Scholar
  4. 4.
    Mai, T.A., Suen, C.Y.: A Generalized Knowledge Based System for The Recognition of Unconstrained Handwritten Numerals. IEEE Trans. on Systems, Man, and Cybernetics 20(4), 835–848 (1980)CrossRefGoogle Scholar
  5. 5.
    Knerr, S., Personnaz, L., Dreyfus, G.: Handwritten Digit Recognition by Neural Networks with Singlelayer Training. IEEE Trans. Neural Networks 3(6), 962–968 (1992)CrossRefGoogle Scholar
  6. 6.
    Mohiuddin, K.M., Mao, J.: A Comparative Study of Different Classifiers for Handprinted Character Recognition. Pattern Recognition in Practice IV, 437–448 (1994)Google Scholar
  7. 7.
    Wang, J.: Resolving Multifont Character Confusion with Neural Networks. Pattern Recognition 26(1), 175–187 (1993)CrossRefGoogle Scholar
  8. 8.
    Huang, Y.S., Suen, C.Y.: A Method of Combining Multiple Experts for The Recognition of Unconstrained Handwritten Numerals. IEEE Trans. PAMI 17(1) (1995)Google Scholar
  9. 9.
    Cho, S.B., Kim, J.H.: Multiple Network Fusion Using Fuzzy Logic IEEE Trans. Neural Networks 6(2), 487–501 (1995)Google Scholar
  10. 10.
    Lee, S.W., Kim, Y.J.: Multiresolution Recognition of Handwritten Numerals with Wavelet Transform and Multilayer Cluster Neural Network. In: 3rd international conference on document analysis and recognition, pp. 1010–1031 (1995)Google Scholar
  11. 11.
    Suen Ching, Y., et al.: Computer Recognition of Unconstrained Handwritten Numerals. Proceeding of the IEEE 80(7), 1162–1180 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Kyoung Min Kim
    • 1
    • 4
  • Joong Jo Park
    • 2
  • Young Gi Song
    • 3
  • In Cheol Kim
    • 1
  • Ching Y. Suen
    • 1
  1. 1.Centre for Pattern Recognition and Machine Intelligence (CENPARMI)Concordia UniversityMontrealCanada
  2. 2.Department of Control and Instrumentation EngineeringGyeongsang National UniversityGyeongnamKorea
  3. 3.Hyundai Information Technology Research CenterYongin City, KyonggidoKorea
  4. 4.Department of Electrical EngineeringYosu National UniversityChonnamKorea

Personalised recommendations