Video data mining based on information fusion for tamper detection

Girija Chetty, Renuka Biswas

Research output: Contribution to journalArticle

Abstract

In this paper, we propose novel algorithmic models based on information fusion and feature transformation in crossmodal subspace for different types of residue features extracted from several intra-frame and inter-frame pixel sub-blocks in video sequences for detecting digital video tampering or forgery. An evaluation of proposed residue features - the noise residue features and the quantization features, their transformation in cross-modal subspace, and their multimodal fusion, for emulated copy-move tamper scenario shows a significant improvement in tamper detection accuracy as compared to single mode features without transformation in cross-modal subspace.

Original languageEnglish
Pages (from-to)1104-1111
Number of pages8
JournalWorld Academy of Science, Engineering and Technology
Volume5
Issue number5
Publication statusPublished - 1 May 2011
Externally publishedYes

Fingerprint

Information fusion
Data mining
Pixels

Cite this

@article{c086e88211564261b09c43342a82cd7e,
title = "Video data mining based on information fusion for tamper detection",
abstract = "In this paper, we propose novel algorithmic models based on information fusion and feature transformation in crossmodal subspace for different types of residue features extracted from several intra-frame and inter-frame pixel sub-blocks in video sequences for detecting digital video tampering or forgery. An evaluation of proposed residue features - the noise residue features and the quantization features, their transformation in cross-modal subspace, and their multimodal fusion, for emulated copy-move tamper scenario shows a significant improvement in tamper detection accuracy as compared to single mode features without transformation in cross-modal subspace.",
keywords = "Correlation features image fusion, Digital forensics, Image tamper detection",
author = "Girija Chetty and Renuka Biswas",
year = "2011",
month = "5",
day = "1",
language = "English",
volume = "5",
pages = "1104--1111",
journal = "World Academy of Science, Engineering and Technology",
issn = "2010-376X",
publisher = "World Academy of Science Engineering and Technology",
number = "5",

}

Video data mining based on information fusion for tamper detection. / Chetty, Girija; Biswas, Renuka.

In: World Academy of Science, Engineering and Technology, Vol. 5, No. 5, 01.05.2011, p. 1104-1111.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Video data mining based on information fusion for tamper detection

AU - Chetty, Girija

AU - Biswas, Renuka

PY - 2011/5/1

Y1 - 2011/5/1

N2 - In this paper, we propose novel algorithmic models based on information fusion and feature transformation in crossmodal subspace for different types of residue features extracted from several intra-frame and inter-frame pixel sub-blocks in video sequences for detecting digital video tampering or forgery. An evaluation of proposed residue features - the noise residue features and the quantization features, their transformation in cross-modal subspace, and their multimodal fusion, for emulated copy-move tamper scenario shows a significant improvement in tamper detection accuracy as compared to single mode features without transformation in cross-modal subspace.

AB - In this paper, we propose novel algorithmic models based on information fusion and feature transformation in crossmodal subspace for different types of residue features extracted from several intra-frame and inter-frame pixel sub-blocks in video sequences for detecting digital video tampering or forgery. An evaluation of proposed residue features - the noise residue features and the quantization features, their transformation in cross-modal subspace, and their multimodal fusion, for emulated copy-move tamper scenario shows a significant improvement in tamper detection accuracy as compared to single mode features without transformation in cross-modal subspace.

KW - Correlation features image fusion

KW - Digital forensics

KW - Image tamper detection

UR - http://www.scopus.com/inward/record.url?scp=79959574245&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 1104

EP - 1111

JO - World Academy of Science, Engineering and Technology

JF - World Academy of Science, Engineering and Technology

SN - 2010-376X

IS - 5

ER -