Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지

Recognition of Unconstrained Handwritten Digits Using Raised Cosine RBF Neural Networks

Raised Cosine RBF 신경망을 이용한 무제약 필기체 숫자 인식

  • 박준근 (금오공과대학교 전자공학과) ;
  • 김상희 (금오공과대학교 전자공학부) ;
  • 박원우 (금오공과대학교 전자공학과)
  • Published : 2002.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we presented a new approach to the recognition of unconstrained handwritten numerals using an improved RBF(Radial Basis Function) Neural Networks. The RBF Neural Networks used Raised Cosine as a basis function to improve discrimination and reduce processing time. The performance of Raised Cosine RBF Neural Networks classifier was evaluated using totally unconstrained handwritten numeral database of Concordia University, Montreal, Canada, and the experimental results showed the recognition rate of 98.05%.

본 논문에서는 무제약 필기체 숫자 인식에 있어서 향상된 RBF(Radial Basis Function) 신경망을 이용한 새로운 접근 방법을 제시하였다. RBF 신경망은 인식률과 인식 속도를 향상시키기 위해 기저 함수로서 Raised Cosine RBF를 사용하였다. Raised Cosine RBF 신경망 분류기의 성능 평가를 위하여 캐나다 몬트리올 Concordia 대학의 무제약 필기체 숫자 데이터베이스를 사용하였고, 실험 결과 98.05%의 인식률을 보였다.

Keywords

References

  1. IEEE Control System Magazine Introduction to Neural Networks for Intelligent Control B. Bavarian
  2. IEEE Trans. on Neural Networks. v.8 no.2 A New Recurent Neural Network Architecture for Visual Pattern Recognition Seong-when Lee, Hee-heon Song
  3. Digital Image Processing W. K. Pratt
  4. Neural Networks Simon Haykin
  5. IEEE Trans. on Neural Networks v.12 no.1 Approximation of Nonlinear Systems with Radial Basis Function Neural Networks Robert J. Schilling, James J. Carroll;Ahmad F. Al-Ajlouni
  6. Proc. IEEE International Conference on Neural Networks v.3 Gradient Descent Learning of Radial Basis Neural Networks N. B. Karayiannis
  7. 신호처리·시스템 학회 논문지 v.2 no.1 수정된 카오스 신경망을 이용한 무제약 서체 숫자 인식 최한고, 김상희, 이상재
  8. IEEE Trans. on Neural Networks v.7 no.2 Unconstrained Handwritten Numeral Recognition Based on Radial Basis Competitive and Cooperative Networks with Spatio-Temporal Feature Representation Sukhan Lee, Jack Chien Pan
  9. 한국정보과학회 논문지 v.21 no.8 유전자 알고리듬과 다층 클러스터 신경망을 이용한 무제약 필기체 숫자의 오프라인 인식 김영준, 이성환
  10. Proc. 1st Int. Workshop on Frontiers in Handwriting Recognition Unconstraind Handwritten Character Classification Using Modifed Backpropagation Model A. Krzyzak, W. Dai;C.Y.Suen
  11. Computer Vision and Shape Recognition Contour Tracing and Parametric Approximations for Digitized Patterns R. Legault;C. Y. Suen