DOI QR코드

DOI QR Code

Machine Printed Character Recognition Based on the Combination of Recognition Units Using Multiple Neural Networks

다중 신경망을 이용한 인식단위 결합 기반의 인쇄체 문자인식

  • 임길택 (한국전자통신연구원 우정기술연구센터) ;
  • 김호연 (한국전자통신연구원 우정기술연구센터) ;
  • 남윤석 (한국전자통신연구원 우정기술연구센터)
  • Published : 2003.12.01

Abstract

In this Paper. we propose a recognition method of machine printed characters based on the combination of recognition units using multiple neural networks. In our recognition method, the input character is classified into one of 7 character types among which the first 6 types are for Hangul character and the last type is for non-Hangul characters. Hangul characters are recognized by several MLP (multilayer perceptron) neural networks through two stages. In the first stage, we divide Hangul character image into two or three recognition units (HRU : Hangul recognition unit) according to the combination fashion of graphemes. Each recognition unit composed of one or two graphemes is recognized by an MLP neural network with an input feature vector of pixel direction angles. In the second stage, the recognition aspect features of the HRU MLP recognizers in the first stage are extracted and forwarded to a subsequent MLP by which final recognition result is obtained. For the recognition of non-Hangul characters, a single MLP is employed. The recognition experiments had been performed on the character image database collected from 50,000 real letter envelope images. The experimental results have demonstrated the superiority of the proposed method.

References

  1. 권재욱, 조성배, 김진형, '계층적 신경망을 이용한 다중 크기의 다중활자체 한글문서 인식', 한국정보과학회논문지, 제19권 제1호, pp.69-79, 1992
  2. S. B. Cho and J. H. Kim, 'Hierarchically structured neural networks for printed Hangul character recognition,' International Joint Conference on Neural Networks, Vol.1, pp.265-270, 1990 https://doi.org/10.1109/IJCNN.1990.137580
  3. 이진수, 권오준, 방승양, '개선된 자소 인식 방법을 통한 고인식률 인쇄체 한글 인식', 한국정보과학회논문지, 제23권 제8호, pp.841-851, 1996
  4. 이판호, 장희돈, 남궁재찬, '동적자소분할과 신경망을 이용한 인쇄체 한글 문자인식에 관한 연구', 한국통신학회논문지, 제19권 제1호, pp.2133-2145, 1994
  5. 최동혁, 류성원, 강현철, 박규태, '계층구조 신경망을 이용한 한글 인식', 대한전자공학회논문지, 제28권 B편 제11호, pp.1-7, 1991
  6. 김우태, 윤병식, 박인규, 진성일, '인쇄체 한글 문자인식을 위한 특징성능의 비교', 한국정보과학회논문지, 제20권 제8호, pp.1103-1110, 1993
  7. S. I. Chien, 'Hangul(Korean) and English OCR system using multiple hypothesis driven neural nets,' Korean-French Character Recognition Workshop, pp.37-52, 1994
  8. 장명욱, 천대녕, 양현승, '연결화소를 이용한 문서 영상의 분할 및 인식', 한국정보과학회논문지, 제20권 제12호, pp.1741-1751, 1993
  9. 이성환, '다양한 활자체 및 크기를 갖는 대용량 한글의 고속 인식을 위한 최적 트리 분류기', 한국정보과학회논문지, 제20권 제8호, pp.1083-1092, 1991
  10. 김정우, 이행세, '인쇄체 한글 및 한자의 인식에 관한 연구', 한국통신학회논문지, Vol.17, No.11, pp.1175-1184, 1992
  11. H. Kim and J. Kim, 'Hierarchical random graph representation of hanwritten characters and its application to Hangul recognition,' Pattern Recognition, Vol.34, pp.187-201, 2001 https://doi.org/10.1016/S0031-3203(99)00222-8
  12. S. Jeong, K. Lim and Y. Nam, 'A combination method of two classifiers based on the information of confusion matrix,' International Workshop on Frontiers in Handwriting Recognition, pp.519-523, 2002 https://doi.org/10.1109/IWFHR.2002.1030963
  13. K. Kim, J. Kim, and C. Suen, 'Segmentation-based recognition of handwritten touching pairs of digits using structural features,' Pattern Recognition Letters, Vol. 23, pp.13-24, 2002 https://doi.org/10.1016/S0167-8655(01)00114-3
  14. G. Kim and V. Govindaraju, 'A Lexicon driven approach to handwritten word recognition for real-time applications,' IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.19, No.4, pp.366-379, 1997 https://doi.org/10.1109/34.588017
  15. 김호연, 임길택, 김두식, 남윤석, '서장 우편물 자동처리를 위한 우편영상 인식 시스템', 정보처리학회논문지B, 제10-B권 제4호, pp.429-442, 2003 https://doi.org/10.3745/KIPSTB.2003.10B.4.429
  16. D. E. Rumelhart, G. E. Hinton and R. J. Williams, 'Learning internal representations by error propagation,' Parallel Distributed Processing, Vol.1, pp.319-362, 1986