A Novel Approach to Video Copy Detection Using Audio Fingerprints and PCA

In Content-Based Copy detection(CBCD)literature, numerous state-of-the-art techniques are primarily focusing on visual content of video. Exploiting audio fingerprints for CBCD problem is necessary, because of following reasons: audio content constitutes an indispensable information source;transforma...

Full description

Saved in:
Bibliographic Details
Published inProcedia computer science Vol. 5; pp. 149 - 156
Main Authors Roopalakshmi, R., Reddy, G. Ram Mohana
Format Journal Article
LanguageEnglish
Published Elsevier B.V 2011
Subjects
audio fingerprints
Content-based video copy detection
MFCC
PCA
Spectral Descriptors
audio fingerprints
Spectral Descriptors
MFCC
Content-based video copy detection
PCA
Online AccessGet full text

Cover

More Information
Summary:In Content-Based Copy detection(CBCD)literature, numerous state-of-the-art techniques are primarily focusing on visual content of video. Exploiting audio fingerprints for CBCD problem is necessary, because of following reasons: audio content constitutes an indispensable information source;transformations on audio content is limited compared to visual content. In this paper, a novel CBCD approach using audio features and PCA is proposed, which includes two stages:first, multiple feature vectors are computed by utilizing MFCC and four spectral descriptors;second, features are further processed using PCA, to provide compact feature description. The results of experiments tested on TRECVID-2007 dataset, demonstrate the e_ciency of proposed method against various transformations.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2011.07.021