A confidence based recognition system for TV commercial extraction

Li, Yijun, Zhang, Danqing, Zhou, Xiangmin and Jin, Jesse S. (2008). A confidence based recognition system for TV commercial extraction. In: Database Technologies 2008 - Proceedings of the Nineteenth Australasian Database Conference, ADC 2008. 19th Australasian Database Conference, ADC 2008, Wollongong, NSW, (57-64). 1 January 2008.

Author Li, Yijun
Zhang, Danqing
Zhou, Xiangmin
Jin, Jesse S.
Title of paper A confidence based recognition system for TV commercial extraction
Conference name 19th Australasian Database Conference, ADC 2008
Conference location Wollongong, NSW
Conference dates 1 January 2008
Proceedings title Database Technologies 2008 - Proceedings of the Nineteenth Australasian Database Conference, ADC 2008
Journal name Conferences in Research and Practice in Information Technology Series
Series Australian computer science communications, v. 30, no. 2.; Conferences in research and practice in information technology series
Place of Publication Sydney, NSW Australia
Publisher Australian Computer Society in association with the ACM Digital Library
Publication Year 2008
Year available 2008
Sub-type Fully published paper
Open Access Status
ISBN 1920682562
9781920682569
ISSN 1445-1336
Volume 75
Start page 57
End page 64
Total pages 8
Collection year 2009
Language eng
Abstract/Summary Automatic real-time recognition of TV commercials is an essential step for TV broadcast monitoring. It comprises two basic tasks: rapid detection of known commercials that are stored in a database, and accurate recognition of unknown ones that appear for the first time in TV streaming. The existing approaches, however, can not perform robust commercial detection because they highly rely on the assumption that black frames are inserted before commercial breaks. In this paper, we propose a novel confidence-based recognition system to address this challenging issues. Those known commercials are detected by applying a fast search algorithm to a pre-built commercial database, and those unknown ones are determined by managing a buffer containing possible yet unconfirmed commercial spots. A new concept of confidence level is defined for each candidate, there-fore commercial breaks can be accurately determined based on a confidence threshold. Experimental results using two 48-hour TV broadcasting indicate the high performance of our proposed method.
Subjects 1705 Computer Networks and Communications
1706 Computer Science Applications
1708 Hardware and Architecture
1710 Information Systems
1712 Software
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Thu, 28 Nov 2013, 11:55:42 EST by System User on behalf of School of Information Technol and Elec Engineering