The Transactions of the Korea Information Processing Society (한국정보처리학회논문지)

Korea Information Processing Society (한국정보처리학회)
권호 표지

handwritten Numeral Recognition Based on Modular Neural Networks Utilizing Rotated and Translated Images

회전 및 이동 영상을 이용하는 모듈 구조 신경망 기반 필기체 숫자 인식

  • 임길택 (한국전자통신연구원 우정기술연구부) ;
  • 남윤석 (한국전자통신연구원 우정기술연구부) ;
  • 진성일 (경북대학교 전자전기공학부)
  • Published : 2000.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

Keywords

References

  1. A. Krzyzak W. Dai, and C. Y Suen, 'Unconstrained handwrittlen character classification using modified backpropagation model,' Proc of the First IWFHR, Montreal, Canada, pp.155- 166, 1990
  2. S. Cho, 'Neural-network classifiers for recognizing totally unconstrained handwritten numerals,' IEEE Transactions on Neural Networks, Vol.8, pp.43-53, 1997 https://doi.org/10.1109/72.554190
  3. T.Akiyama and N. Hagita, 'Automated entry system for printed documents,' Pattern Recognition, Vol.23. pp.1141 -1154, 1990 https://doi.org/10.1016/0031-3203(90)90112-X
  4. J H Kim, K. Kim, and S Chien, 'Korean and English character recognition system using hierarchical classification neural network,' Proc. of ICSMC, Vancouver, Vol.1 pp759-764, Oct. 1995 https://doi.org/10.1109/ICSMC.1995.537856
  5. D. Lee and S N Srihari, 'A theory of classifier combination :the neural network approach,' Proc. of the Third ICDAR, Montreal, Canada, pp.42-45, 1995 https://doi.org/10.1109/ICDAR.1995.598940
  6. T. K. Ho, J J Hull, and S. N. Srihari, 'Decision combination in multiple classifier systems,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.16, pp.66-75, 1994 https://doi.org/10.1109/34.273716
  7. Y. S. Huang and C. Y. Suen, 'A method of combining multiple experts for the recognition of unconstrained handwritten numerals,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.17, pp.90-94. 1995 https://doi.org/10.1109/34.368145
  8. K. Miyahara and F. Yoda, 'Printed Japanese character recognition based on multiple modified LVQ neural network,' ICDAR, Tsukuba, PP 250-253, 1993 https://doi.org/10.1109/ICDAR.1993.395738
  9. S. N. Srihari, 'Recognition of handwritten and machine printed text of postal address interpretation,' Pattern Recognition Letters, Vol.14, pp 291-302, 1993 https://doi.org/10.1016/0167-8655(93)90095-U
  10. Y. M Baek, K. T. Lim, and S. I. Chien, 'Off-line handwritten Hangul recognition based on multiple features and modular partially connected multi-layer perceptrons,' Proc. of IWFHR, Taejon, pp.269- 278. 1998
  11. L. Xu. A. Krzyzak, and C. Y. Suen, 'Method of combining multiple classifiers and their application to handwritten numeral recognition,' IEEE Transactions on Systems, Man. and Cybernetics, Vol 22, pp. 418-435, 1992 https://doi.org/10.1109/21.155943
  12. F. Kimura and M. Shridhar, 'Handwritten numeral recognition based on multiple algorithms,' Pattern Recognition , Vol. 24 , No.10. pp 976-983, 1991
  13. J. Cao. M. Ahmadi, and M. Shridhar, 'Recognition of handwritten numerals with multiple feature and multistage classifier,' Pattern Recognition. Vol.28, No.2, pp.1153-160, 1995
  14. A. Waibel. H. Sawai, and K. Shikano, 'Modularity and scaling in large phonemic neural networks,' IEEE Transactions on Acoustics, Speech; and Signal Processing, Vol.37, pp.1888- 1898, 1989 https://doi.org/10.1109/29.45535
  15. B. S. Kang, S. I. Chien, and K. T. Lim, 'Large scale pattern recognition system usIng hierarchical neural network and false alarming nodes,' Proc. of ICTAI, Newport. California, pp 196-203, Nov. 1997 https://doi.org/10.1109/TAI.1997.632256
  16. C. Y. Suen, C. Nadal, R. Legault, T A Mai, and L. Lam, 'Computer recognition of unconstrained handwritten numerals,' Proc of IEEE, Vol.80, No.7, pp, 1162-1180, 1992 https://doi.org/10.1109/MWSCAS.2003.1562448
  17. F. Togawa, T. Ueda, T. Aramaki. and A. Tanaka, 'Receptive field neural network wtth shift tolerant capability for Kanji character recognition,' IJCNN, pp.1490-1499, 1988
  18. A. Itawa. H. Kawajiri, and N. Suzumura, 'Classification of handwritten digits by a large scale neural network 'CombNET-II',' IJCNN, Singapore, Vol.1, pp 1021- 1026. Nov. 1991 https://doi.org/10.1109/IJCNN.1991.170531
  19. M. Nadler and E. Smith, Pattern Recognition Engineering, John Wiley & Sons, New York. 1993
  20. T Kohonen, 'The self-organizing map,' Proc. of IEEE, Vol 78, No 9, pp.1464-1480, 1990 https://doi.org/10.1109/5.58325
  21. S. Lee and I. Park, 'Nonlinear shape normalization methods for the recognition of large-set handwritten characters,' Pattern Recognition, Vol.27, No.7, pp 895-902. 1994 https://doi.org/10.1016/0031-3203(94)90155-4
  22. H. S. Baird, 'Document image defect models,' IAPR Workshop on SSPR, Murray Hill, NJ. pp.38-46, 1990
  23. H. Takahashi, 'A neural network OCR using geometrical and zonal pattern features,' Proc. of ICDAR, Pans, Vol 2, pp.821-823. 1991
  24. G. Srikantan, S. W. Lam, nnd S. N. Srihari. 'Gradient-based contour encoding for character recognition,' Pattern Recognition, Vol.29, pp.1147-1160, 1996 https://doi.org/10.1016/0031-3203(95)00146-8
  25. R. Gonzalez and R. Woods, Digital Image Processing, Addison Wesley. pp.148-156, 1989