메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
This paper presents a heuristic method for extracting recognition fields in a GIRO ship image. The image contains several text lines to be recognized, and they are located at a fixed area and at a non-fixed area. Since one of the text lines is in the non-fixed area of a relatively big area, we call the slip a loosely constrained form. There are two major steps in the process: text line assumption and field selection from the assumed text lines. To assume the text lines a combined top-down and bottom-up image analysis is used. It is done by a recursive X-Y cut on the projection profiles of the connected components (top-down) and by analyzing the relative locations of the components and merging the neighboring components (bottom-up). The combined approach gives improvement in processing speed and extraction accuracy. To select the recognition fields in the fixed area size and location constraints of assumed text lines are used. And to select the field in the non-fixed area two more constraints of global shape of the field and local character composition by defining and measuring contour length factor (CLF) were used. We have tested the method with 245 real GIRO images and the fields were extracted correctly from 192 (78.4%) test images.

목차

Abstract

Ⅰ. Introduction

Ⅱ. Recognition Field Extraction

Ⅲ. Experimental Results

Ⅳ. Conclusions

References

저자소개

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2009-569-017770275