Self-generation ART Neural Network for Character Recognition

  • Taekyung Kim
  • Seongwon Lee
  • Joonki Paik
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)


In this paper, we present a novel self-generation, supervised character recognition algorithm based on adaptive resonance theory (ART) artificial neural network (ANN) and delta-bar-delta method. By combining two methods, the proposed algorithm can reduce noise problem in the ART ANN and the local minima problem in the delta-bar-delta method. The proposed method can extend itself based on new information contained in input patterns that require nodes of hidden layers in neural networks and effectively find characters. We experiment with various real-world documents such as a student ID and an identifier on a container. The experimental results show that the proposed self-generation. ART algorithm reduces the possibility of local minima and accelerates learning speed compared with existing.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Rumelhart, D., Hinton, G., Williams, R.J.: Learning Representation by Back Propagation Errors. Nature, 533–536 (1986)Google Scholar
  2. Rumelhart, D., McClelland, J.: The PDP Research Group. Parallel Distributed Processing 1, 318–536Google Scholar
  3. James, A., David, M.: Neural Networks Algorithms, Applications, and Programming Techiques, pp. 89–125. Addison Wesley, Reading (1991)Google Scholar
  4. Martin, T., Howard, B.: Neural Network Design. PWS Publishing Company (1996)Google Scholar
  5. Carpenter, G., Grossberg, S.: Neural Dynamics of Category Learning and Recognition, Attention, Memory Consolidation, and Amnesia. Brain Structure, Learning, and Memory, AAAS Symposium Series (1986)Google Scholar
  6. Carpenter., G., Grossberg, S.: The ART of Adaptive Pattern Recognition by a Self-Organizing Neural networks. IEEE Computers, 77–88 (1988)Google Scholar
  7. Kim, K., Kim, K.C.: A Study on Face Recognition using New Fuzzy ART. ITC-CSCC 2, 1057–1060 (1998)Google Scholar
  8. Carpenter, G., Grossberg, S.: A Massively Parallel Architecture for a Self-organizing Neural Pattern Recognition Machine. Computer Vision, Graphics, and Image Processing 37, 54–115 (1987)CrossRefGoogle Scholar
  9. Allen, R.: Several Studies on Natural Language and Back Propagation. IEEE ICNN 2, 335–342 (1987)Google Scholar
  10. Jacobs, R.A.: Increased Rates of Convergence Through Learning Rate Adaptation. Neural Networks 2, 295–308 (1988)CrossRefGoogle Scholar
  11. Carpenter, G., Grossberg, S.: ART2 Self-Organization of Stable Category Recognition Codes for Analog Input Patterns. In: 1987 IEEE Int. Conf. Neural Networks, pp. 727–736 (1987)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Taekyung Kim
    • 1
  • Seongwon Lee
    • 2
  • Joonki Paik
    • 1
  1. 1.Image Processing and Intelligent Systems Laboratory, Department of Image Engineering, Graduate School of Advanced Imaging Science, Multimedia, and FilmChung-Ang UniversitySeoulKorea
  2. 2.Department of Computer Engineering, College of Electronics and InformationKwangwoon UniversitySeoulKorea

Personalised recommendations