CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
A Unified Framework for Tracking Based Text Detection and Recognition from Web Videos
Tian, Shu1; Yin, Xu-Cheng2; Su, Ya1; Hao, Hong-Wei3
Source PublicationIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
2018-03-01
Volume40Issue:3Pages:542-554
SubtypeArticle
AbstractVideo text extraction plays an important role for multimedia understanding and retrieval. Most previous research efforts are conducted within individual frames. A few of recent methods, which pay attention to text tracking using multiple frames, however, do not effectively mine the relations among text detection, tracking and recognition. In this paper, we propose a generic Bayesian-based framework of Tracking based Text Detection And Recognition (T(2)DAR) from web videos for embedded captions, which is composed of three major components, i.e., text tracking, tracking based text detection, and tracking based text recognition. In this unified framework, text tracking is first conducted by tracking-by-detection. Tracking trajectories are then revised and refined with detection or recognition results. Text detection or recognition is finally improved with multi-frame integration. Moreover, a challenging video text (embedded caption text) database (USTB-VidTEXT) is constructed and publicly available. A variety of experiments on this dataset verify that our proposed approach largely improves the performance of text detection and recognition from web videos.
KeywordVideo Text Extraction Text Tracking Tracking Based Text Detection Tracking Based Text Recognition Embedded Captions
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TPAMI.2017.2692763
WOS KeywordNATURAL SCENE IMAGES ; READING TEXT ; SEGMENTATION ; EXTRACTION
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China(61473036)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000424465900003
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/21959
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation1.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Dept Comp Sci & Technol, Beijing 100083, Peoples R China
2.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Dept Comp Sci & Technol, Beijing Key Lab Mat Sci Knowledge Engn, Beijing 100083, Peoples R China
3.Chinese Acad Sci, Res Ctr Digital Technol, Inst Automat, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Tian, Shu,Yin, Xu-Cheng,Su, Ya,et al. A Unified Framework for Tracking Based Text Detection and Recognition from Web Videos[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(3):542-554.
APA Tian, Shu,Yin, Xu-Cheng,Su, Ya,&Hao, Hong-Wei.(2018).A Unified Framework for Tracking Based Text Detection and Recognition from Web Videos.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(3),542-554.
MLA Tian, Shu,et al."A Unified Framework for Tracking Based Text Detection and Recognition from Web Videos".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.3(2018):542-554.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tian, Shu]'s Articles
[Yin, Xu-Cheng]'s Articles
[Su, Ya]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tian, Shu]'s Articles
[Yin, Xu-Cheng]'s Articles
[Su, Ya]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tian, Shu]'s Articles
[Yin, Xu-Cheng]'s Articles
[Su, Ya]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.