한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

신경회로망과 퍼지 추론에 의한 필기체 숫자 인식

Recognition of Handwritten Digits Based on Neural Network and Fuzzy Inference

  • 고창룡 (부산대학교 전자공학과, 부산교육연구정보원)
  • Ko, Chang-Ryong (Dept. of Electonic Engineering, Busan National University, Busan Education Research & Information Center)
  • 투고 : 2011.09.01
  • 심사 : 2011.09.23
  • 발행 : 2011.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 퍼지추론을 이용하여 신경회로망의 필기체 숫자 인식 개선 방법을 제안하였고 실험을 통하여 확인하였다. 신경회로망은 학습 시간이 오래 걸리고, 학습한 패턴에서는 100% 인식률을 보였다. 그러나 신경회로망은 시험 패턴에서는 좋은 결과를 보여주지 못했다. 실험결과 신경회로망의 인식률과 오인식률이 각각 초기 89.6%, 10.4%에서 90.2%, 9.8%로 각각 향상되었다. 특히, 숫자 3과 5에서 오인식률을 크게 감소시켰다. 실험에서 퍼지 소속 함수의 추출을 숫자의 밀도로 사용하였으나 필기체 숫자는 입력 패턴이 다양하기 때문에 다양한 특성을 추출하고 복합적으로 퍼지 추론을 사용해 더 나은 인식률을 높여야 한다. 또한 퍼지추론을 엄격하게 적용하기보다는 입력 패턴을 매칭 할 때 퍼지 추론을 적용하는 것을 제안한다.

We present a method to modify the recognition of neural networks by the fuzzy inference in a handwritten digit recognition with large deformations, and we verified the method by the experiment. The neural networks take long time in learning and recognize 100% on the learning pattern. But the neural networks don't show a good recognition on the testing pattern. So, we apply the modified method as the fuzzy inference. As a result, the recognition and false recognition of neural networks was improved 90.2% and 9.8% respectively at 89.6% and 10.4% initially. This approach decreased especially the false recognition on digit 3, 5. We used the density of digit to extract the fuzzy membership function in this experiment. But, because the handwritten digit have varified input patterns, we will get a better recognition by extracting varifed characteristics and applying the composite fuzzy inference. We also propose the application of fuzzy inference on matching the input pattern, than applying strictly the fuzzy inference.

키워드

참고문헌

  1. E. H. Mamdani, "Application of fuzzy algorithm for control of simple dynamic plant", IEEE Proc. Control and Science, Vol.121, No.12, pp.1585-1588, Dec 1974.
  2. M. W. Kim, S. Y. Bang, Easy Neural Network Computer, The Electronics Times, Oct 1992.
  3. Seung Yeob Baeg, Dong Hoon Kim, Ho Sun Chung, "The Recognition of Korean Character Using Preceding Layer Driven MLP ", The Institute of Electronics Engineers of KOREA, Vol. 28, No 5, pp.65-76, May 1991.
  4. J. M. Zurada, Introduction to Artifical Neural System, West Publishing Co., 1992.
  5. H. L. Jeon, H. C. Cho, "Fusion Technique of Fuzzy Neural Network", The Institute of Electronics Engineers of KOREA, Vol. 18, No. 10, pp.775-780, Oct 1991.
  6. J. K. Um, S. H. Won, Fuzzy Theory and System, Jungbosidae, Sep 1992.
  7. Hyroyoshi Nomura, Isao Hayashi, Nobora Wakami, "A Learning Method of Fuzzy Inference Rules by Descent Method,", IEEE International Conference on Fuzzy Systems, pp.203-210, Mar 1992.
  8. K. W. Lim, Y. H. Kim, H. Kang, H. T. Jeon, "Neural-fuzzy Convergence of the Automatic Generation of Fuzzy Control Rules", The Institute of Electronics Engineers of KOREA, Vol. 29, No. 11, pp.1066-1075, Nov 1992.
  9. S. Horikawa, T. Furuhasi, S. Okuma, and Y. Uchikawa, "Composition Methods of Fuzzy Neural Networks", Proc. of IECON, Vol.2, pp.1253-1258, Nov 1990.
  10. Yasuhiko Dote, "Fuzzy and Neural Network Controller", Proc. of IECON, Vol.2, pp.1315-1343, Nov 1990.
  11. D. E. Rumelhalt and J. L. McClelland, Parallel Distributed Processing, MIT Press, Cambridge, July 1987.
  12. H. G. Lee, D. J. Sung, S. Y. Bang, "Hangul Character Recognition with Neural Networks", The Institute of Electronics Engineers of KOREA, Vol. 8, No. 10, pp.727-737, Oct 1991.
  13. G. K. Sierra, J. O. Bulla, M. A. Melgarejo, "An Embedded Type-2 Fuzzy Processor For The Inverted Pendulum Control Problem", IEEE Latin America Transactions, Vol. 9, No. 3, pp.240-246, June 2011. https://doi.org/10.1109/TLA.2011.5893768
  14. Mahdi Khezri, Mehran Jahed, "A Neuro--Fuzzy Inference System for sEMG-Based Identification of Hand Motion Commands", IEEE Transactions on Industrial Electonics, Vol. 58, No. 5, May 2011.
  15. William-Chandra Tjhi, Lihui Chen, "Dual Fuzzy Possibilistic Coclustering for Categorization of Documents", IEEE Transactions on Fuzzy Systems, Vol. 17, No. 3, June 2009.

피인용 문헌

  1. An Acceleration Method for Symmetry Detection using Edge Segmentation vol.20, pp.9, 2015, https://doi.org/10.9708/jksci.2015.20.9.031
  2. Symmetry Detection Through Hybrid Use Of Location And Direction Of Edges vol.21, pp.4, 2011, https://doi.org/10.9708/jksci.2016.21.4.009