ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Automatic Container Code Recognition from Multiple Views
Cited 9 time in scopus Download 7 time Share share facebook twitter linkedin kakaostory
저자
윤영우, 반규대, 윤호섭, 김재홍
발행일
201608
출처
ETRI Journal, v.38 no.4, pp.767-775
ISSN
1225-6463
출판사
한국전자통신연구원 (ETRI)
DOI
https://dx.doi.org/10.4218/etrij.16.0014.0069
협약과제
13SE1600, 시각 생체 모방 소자 및 인지 시스템 기술 개발, 정명애
초록
Automatic container code recognition from a captured image is used for tracking and monitoring containers, but often fails when the code is not captured clearly. In this paper, we increase the accuracy of container code recognition using multiple views. A character-level integration method combines recognized codes from different single views to generate a new code. A decisionlevel integration selects the most probable results from the codes from single views and the new integrated code. The experiment confirmed that the proposed integration works successfully. The recognition from single views achieved an accuracy of around 70% for the test images collected on a working pier, whereas the proposed integration method showed an accuracy of 96%.
키워드
Character recognition, Container code recognition, Container mark identification, Multiple views
KSP 제안 키워드
Integration method, Multiple views, character recognition, character-level, container code recognition