Matching commercial clips from TV streams using a unique, robust and compact signature

Li, Yijun, Jin, Jesse S. and Zhou, Xiaofang (2005). Matching commercial clips from TV streams using a unique, robust and compact signature. In: B.C. Lovell, A.J. Maeder, T. Caelli and S. Ourselin, Proceedings of Digital Imaging Computer: Techniques and Applications (DICTA 2005). Digital Imaging Computing: Techniques and Applications (DICTA 2005), Cairns, Australia, (266-272). 6-8 December 2005. doi:10.1109/DICTA.2005.1578137

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Li, Yijun
Jin, Jesse S.
Zhou, Xiaofang
Title of paper Matching commercial clips from TV streams using a unique, robust and compact signature
Conference name Digital Imaging Computing: Techniques and Applications (DICTA 2005)
Conference location Cairns, Australia
Conference dates 6-8 December 2005
Proceedings title Proceedings of Digital Imaging Computer: Techniques and Applications (DICTA 2005)
Place of Publication Piscatawa, NJ, United States
Publisher IEEE Computer Society
Publication Year 2005
Sub-type Fully published paper
DOI 10.1109/DICTA.2005.1578137
ISBN 0769524672
9780769524672
Editor B.C. Lovell
A.J. Maeder
T. Caelli
S. Ourselin
Volume 1
Start page 266
End page 272
Total pages 7
Collection year 2005
Language eng
Abstract/Summary One of critical challenges in automatic recognition of TV commercials is to generate a unique, robust and compact signature. Uniqueness indicates the ability to identify the similarity among the commercial video clips which may have slight content variation. Robustness means the ability to match commercial video clips containing the same content but probably with different digitalization/encoding, some noise data, and/or transmission and recording distortion. Efficiency is about the capability of effectively matching commercial video sequences with a low computation cost and storage overhead. In this paper, we present a binary signature based method, which meets all the three criteria above, by combining the techniques of ordinal and color measurements. Experimental results on a real large commercial video database show that our novel approach delivers a significantly better performance comparing to the existing methods.
Subjects E1
280108 Database Management
700103 Information processing services
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ
Additional Notes Article number 1578137

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 6 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 23 Aug 2007, 21:24:43 EST