Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

A Study on the Number Recognition using Cellular Neural Network

Cellular Neural Network을 이용한 숫자인식에 관한 연구

  • 전흥우 (금오공과대학 전자공학과) ;
  • 김명관 (구미전자공고 전자기계과) ;
  • 정금섭 (구미기능대학 생산자동화과)
  • Published : 2002.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

Cellular neural networks(CNN) are neural networks that have locally connected characteristics and real-time image processing. Locally connected characteristics are suitable for VLSI implementation. It also has applications in such areas as image processing and pattern recognition. In this thesis cellular neural networks are used for feature detection in number recognition at the stage of re-processing. The four or six directional shadow detectors are used in numbers recognition. At the stage of classification, this result of feature detection was simulated by using a multi-layer back Propagation neural network. The experiments indicate that the CNN feature detectors capture good features for number recognition tasks.

셀룰러 뉴럴 네트워크는 국부적 연결특성을 가지고 있어 실시간 이미지처리에 적합한 뉴럴 네크워크이다. 또한 국부적 연결특징은 VLSI구현에 적합하다. 그의 응용분야는 패턴인식과 숫자인식 및 영상처리에 응용되고 있다. 본 논문에서, CNN은 전처리 단계로서 숫자의 특징점 추출에 이용된다. CNN을 이용한 그림자검출은 4내지 6방향으로 검출하여 숫자의 특징점을 방향별로 추출한다. 분류단계에서 이러한 형상자료는 다층BP뉴럴 네트워크의 입력벡터에 적합하도록 압축되어 입력된다. 실험결과 CNN을 통한 숫자인식은 굴림체의 경우96%이상의 인식율을 보여 만족할 만한 결과를 얻었다.

Keywords

References

  1. 이성환, '문자인식의 원리 Ⅰ권, Ⅱ권', 2nd edition, 홍릉과학출판사, 1997
  2. 이성환, '패턴인식의 원리 Ⅰ권, Ⅱ권', 2nd edition, 홍릉과학출판사, 1997
  3. 오창석, '뉴로컴퓨터', 3rd edition, 내하출판사, 2000
  4. H. Suzuki and T. Matsumoto, 'A CNN handwritten character ecognizer', Proc. International Workshop on cellular Neural Networks and Their Application, Budapest, 1990
  5. C. Mead, Analog VlSI and Neural Systems, Reading, MA ; Addision Wesley, 1989
  6. Leon O. Chua and Lin Yang, 'Cellular Neural Networks : Theory', IEEE Transactions on Circuits and Systems, Vol. 35, No. 10. pp. 1257-1272, Oct. 1993 https://doi.org/10.1109/31.7600
  7. Leon O. Chua and Lin Yang, 'Cellular Neural Networks : Applications', IEEE Transactions on Circuits and Systems, Vol. 35, No. 10, pp.1273-1290, Oct. 1993 https://doi.org/10.1109/31.7601
  8. Leon O. Chua and Lin Yang, 'Cellular Neural Networks : The CNN Paradigm', IEEE Transactions on Circuits and Systems-I, Vol. 40, No.3. pp. 147-155, Mar. 1993 https://doi.org/10.1109/81.222795
  9. Josep E. Varrientos and Edgar Sanchez- Sinencio, 'A current-mode cellular neural network implementaton', IEEE Transaction on Circuits and Systems, Vol. 40, No. 3, Mar. 1993
  10. T. Matsumoto. L. O. Chua and H. Suzuki, 'CNN cloning template : shadow detector', IEEE Trans. Circuits and Systems, 37, pp. 1070-1073, 1990 https://doi.org/10.1109/31.56083
  11. Jacek M. Zurada, 'Artificial Neural Systems', 2nd edition, PWS Publishing Company, Boston, pp.185-250, 1995
  12. D. Nguyen, B. Widrow, 'Improving the Learning Speed of Two-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights,' IEEE Int. Joint Conf. on Neural Networks, Vol. Ⅲ, pp.21-26, 1990
  13. Y. J. Kim and S. W. Lee, 'Off-line recognition of unconstrained handwritten digits using multi-layer back propagation neural network combined with genetic algorithm', (in Korean), in Proc. 6th Wkshp. Image Processing Understanding, pp.186-193, 1994