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

논문 기본 정보

자료유형
학술저널
저자정보
Ho Jun Kim (Chung-Ang University) Hak Gu Kim (Chung-Ang University)
저널정보
중앙대학교 영상콘텐츠융합연구소MINT Moving Image & Technology (MINT) MINT: Moving Image & Technology, Vol.3, No.2
발행연도
2023.8
수록면
1 - 5 (5page)
DOI
10.15323/mint.2023.8.3.2.1

이용수

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

초록· 키워드

오류제보하기
The detection of texts in the wild is challenging. In particular, curved and perspective-distorted texts are among the most challenging types in scene text detection. In this study, we proposed a novel character regionaware boundary proposal network to detect the curved direction of texts and texts with perspective distortions. The proposed method consists of two main parts:1) an initial boundary proposal and 2) an adaptive deformation module. First, to detect texts with perspective distortions, we employed a pretrained character region-based text detection model. Several text regions detected by the pretrained model were fed to the adaptive deformation module as an initial boundary proposal. Second, 14 node points were sampled in the adaptive deformation module based on the initial boundary proposal. Their locations were then adjusted iteratively such that the boundary accurately fitted the curved text. Experimental results showed that the proposed method can provide robust text detection for curved and perspective-distorted texts.

목차

Abstract:
1. Introduction
2. Related Works
3. Proposed Method
4. Experiments and Results
5. Discussion
6. Conclusion
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-25-02-091066071