닫기
Loading..

전자정보연구정보센터 ICT 융합 전문연구정보의 집대성

국내 논문지

홈 홈 > 연구문헌 > 국내 논문지 > 한국정보과학회 논문지 > 정보과학회 논문지 B : 소프트웨어 및 응용

정보과학회 논문지 B : 소프트웨어 및 응용

Current Result Document : 2 / 6 이전건 이전건   다음건 다음건

한글제목(Korean Title) Run-Length Code를 이용한 제약없이 쓰여진 한글 필기체 주소열 분할
영문제목(English Title) An Approach to Segmentation of Address Strings of Unconstrained Handwritten Hangul using Run-Length Code
저자(Author) 김경환   윤정석  
원문수록처(Citation) VOL 28 NO. 11 PP. 0813 ~ 0821 (2001. 11)
한글내용
(Korean Abstract)
대부분의 문자 인식기들이 인식대상 영상이 인식단위로 분할되어있다는 가정아래 개발되고 있으나, 실제 필기한글의 분할에 대한 연구는 미미한 실정이다. 본 논문은 Run-length code를 이용한 능동적인 한글 분할방법을 제시한다. 전처리와 인식단위 분할에 응용할 수 있는, 한글의 구조적 특성을 반영한, 기울기 보정 알고리즘을 제안하고, 필기자들의 일반적인 필기 습관과 한글이 갖는 2차원 구조의 특성을 반영하면서 문자의 접촉점을 적극적으로 찾아내기 위한 기초 함수들과 접촉점들의 분류 방법을 제시한다. 임의의 필기자로부터 수집한 필기 한글 주소열 데이타를 이용해 수행한 실험을 통해, 초과분할을 포함하여, 88.2%의 접촉 문자들을 분리할 수 있었다.

영문내용
(English Abstract)
While recognition of isolated units of writing, such as a character or a word, has been extensively studied, emphasis on the segmentation itself has been lacking. In this paper we propose an active segmentation method for handwritten Hangul address strings based on the Run-length code. A slant correction algorithm, which is considered as an important preprocessing step for the segmentation, is presented. Three fundamental candidate estimation functions are introduced to detect the clues on touching points, and the classification of touching types is attempted depending on the structural peculiarity of Hangul. Our experiments show segmentation performance of 88.2% on touching characters with minimal over-segmentation.
키워드(Keyword) 문자 인식기   전처리   필기자  
원문 PDF 다운로드