The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)
- Volume 17 Issue 12
- /
- Pages.1380-1390
- /
- 1992
- /
- 1226-4717(pISSN)
- /
- 2287-3880(eISSN)
A Study on On-line Recognition of Korean Strokes with Sequential Information Using Neural Network
순서정보에 의한 한글자획 온라인 인식을 위한 신경회로망에 관한 연구
- Kim, Gil-Jung (Dept. of Electronics Eng. Pusan National Univ.) ;
- Choi, Sug (Dept. of Electronics Eng. Pusan National Univ.) ;
- Lee, Jong-Hyeok (Dept. of Electronics Eng. Pusan National Univ.) ;
- Nam, Ki-Gon (Dept. of Electronics Eng. Pusan National Univ.) ;
- Yoon, Tae-Hoon (Dept. of Electronics Eng. Pusan National Univ.) ;
- Kim, Jae-Chang (Dept. of Electronics Eng. Pusan National Univ.) ;
- Park, Ui-Yul (Dept. of Electronics Eng. Pusan National Univ.) ;
- Lee, Yang-Sung (Dept. of Electronics Eng. Pusan National Univ.)
- 김길중 (부산대학교 전자공학과) ;
- 최석 (부산대학교 전자공학과) ;
- 이종혁 (부산대학교 전자공학과) ;
- 남기곤 (부산대학교 전자공학과) ;
- 윤태훈 (부산대학교 전자공학과) ;
- 김재창 (부산대학교 전자공학과) ;
- 박의열 (부산대학교 전자공학과) ;
- 이양성 (부산대학교 전자공학과)
- Published : 1992.12.01
Abstract
This paper proposes an on-line recognition system of Korean strokes using multi-layer neural network with tracing the stroke pattern. The system segments the stroke pattern into subpatterns, detects prominent stroke features in the subpatterns and integrates all the activation values of features in the related subpatterns. The activation values of the integrated stroke-specific features represent statistic characteristics of features and contributes for classifying the stroke pattern. Since the informations in Korean strokes are concentrated in the first and last parts of the strokes, the system extracts stroke-specific features in these parts attentatively and infers corner features using the sequential information of the extracted stroke-specific features in the first and last part of strokes the system is relatively simple in structure and rapid in on-line recognition of hand-written Korean strokes.
본 연구에서는 한글자획을 온라인으로 인식하는 다층구조 신경회로망을 제안하였다. 입력되는 자획패턴에 대하여 전자펜의 현재 위치에
Keywords