ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Implementation of Automatic X-rated Video Classification and Management System based on Multimodal Features
Cited 1 time in scopus Download 8 time Share share facebook twitter linkedin kakaostory
저자
임재덕, 이철훈, 최병철, 한승완, 김정녀
발행일
201212
출처
International Journal of Advancements in Computing Technology, v.4 no.23, pp.178-186
ISSN
2005-8039
출판사
차세대융합기술연구원(AICIT)
DOI
https://dx.doi.org/10.4156/ijact.vol4.issue23.21
협약과제
12PI1100, 다자간 협업을 위한 몰입형 스마트워크 핵심기술 개발, 김도영
초록
This paper proposes the automatic X-rated video classification and management system and its implementation. Automatic video classification is based on multimodal features; visual and auditory features. Visual features consist of image-based feature and video-based feature. Some MPEG-7 image descriptors and the rule of thirds are adopted as imaged-based feature for deciding harmfulness of a single video frame. The temporal color histogram feature and the repeated curve-like spectrum feature are used as video-based and audio-based feature respectively. They can detect efficiently the motion and sound properties that are appeared in most indecent scenes. In classifying a video file, we use multi-level decision and classification; feature-level decision, clip-level decision and finally file-level classification. Support vector machine classifier is used at the feature-level decision. Each single feature-based video classification performance has about or a slightly higher than 90% of accuracy and multimodal feature-based video classification performance is improved up to 96.5% of accuracy under our dataset configured with 500 general videos and 500 X-rated videos. The measured performance shows that multimodal approach can be deployed to improve the classification performance. The proposed system also provides the graphical interfaces for classification and management in order to verify and handle the detailed classification results of each video.
KSP 제안 키워드
Classification Performance, Color histogram feature, Feature level, Feature-based, Graphical interfaces, Image-based, Level classification, MPEG-7, Management system, Multi-level, Multimodal Features