MODEL-BASED DECODING METRICS FOR CONTENT IDENTIFICATION

被引：0

作者：

Naini, Rohit ^{[1
]}

Moulin, Pierre ^{[1
]}

机构：

[1] Univ Illinois, Beckman Inst, Coord Sci Lab, 405 N Mathews Ave, Urbana, IL 61801 USA

来源：

2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2012年

关键词：

Content identification; audio; video; hashing; fingerprinting; maximum likelihood decoding;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, decoding metrics are designed for statistical fingerprint-based content identification. A fairly general class of structured codes is considered, and a statistical model for the resulting fingerprints and their degraded versions (following miscellaneous content distortions) is proposed and validated. The Maximum-Likelihood fingerprint decoder derived from this model is shown to considerably improve upon previous decoders based on the Hamming metric. A GLRT test is also proposed and evaluated to deal with unknown distortion channels.

引用

页码：1829 / 1832

页数：4

共 8 条

[1]

Baluja S., 2007, P ICASSP

[2]

Haitsma J, 2002, ISMIR 2002 3 INT C M

[3]

Holotyak S., 2011, P ICASSP 2011 PRAG C

[4] Distance Metric Learning for Content Identification [J].

Jang, Dalwon ;

Yoo, Chang D. ;

Kalker, Ton .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2010, 5 (04) :932-944

[5] Pairwise Boosted Audio Fingerprint [J].

Jang, Dalwon ;

Yoo, Chang D. ;

Lee, Sunil ;

Kim, Sungwoong ;

Kalker, Ton .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2009, 4 (04) :995-1004

[6] Robust Video Fingerprinting Based on Symmetric Pairwise Boosting [J].

Lee, Sunil ;

Yoo, Chang D. ;

Kalker, Ton .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2009, 19 (09) :1379-1388

[7]

Moulin P., 2010, P IEEE WORKSH INF TH

[8] Modeling and Analysis of Correlated Binary Fingerprints for Content Identification [J].

Varna, Avinash L. ;

Wu, Min .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2011, 6 (03) :1146-1159

← 1 →