An improved fingerprint algorithm of 3D-DCT for video fingerprinting

In this paper, a new learned basis set algorithm (3D-LBT) based on 3D-DCT (Discrete Cosine Transform) is proposed for video fingerprinting and matching, in which for different video categories an Adaboost-based machine learning method is applied to each category of videos for selecting suitable sets...

Full description

Saved in:
Bibliographic Details
Published in2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA) pp. 290 - 295
Main Authors Mengge Diao, Yuesheng Zhu, Ziqiang Sun, Xiyao Liu, Limin Zhang
Format Conference Proceeding
LanguageEnglish
Published University of Trieste and University of Zagreb 01.09.2013
Subjects
3D-DCT
adaboost
Algorithm design and analysis
Brightness
copyright protection
Fingerprint recognition
machine learning
Machine learning algorithms
Robustness
Signal processing algorithms
video fingerprint
weighted distance
Online AccessGet full text

Cover

More Information
Summary:In this paper, a new learned basis set algorithm (3D-LBT) based on 3D-DCT (Discrete Cosine Transform) is proposed for video fingerprinting and matching, in which for different video categories an Adaboost-based machine learning method is applied to each category of videos for selecting suitable sets of 3D-DCT coefficients to generate fingerprints, and a weighted distance of fingerprints is also defined for fingerprint matching. Our experimental results have illustrated that the proposed algorithm outperforms the conventional 3D-DCT algorithm and the 3D-RBT (Randomized Basis seT) algorithm in terms of robustness and uniqueness. Moreover, the proposed algorithm has better security performance for copyright applications.
ISSN:1845-5921
DOI:10.1109/ISPA.2013.6703755