Illuminant-Based Transformed Spaces for Image Forensics

Illuminant-Based Transformed Spaces for Image Forensics

Author Carvalho, Tiago Google Scholar
Faria, Fabio A. Autor UNIFESP Google Scholar
Pedrini, Helio Google Scholar
Torres, Ricardo da S. Google Scholar
Rocha, Anderson Google Scholar
Abstract In this paper, we explore transformed spaces, represented by image illuminant maps, to propose a methodology for selecting complementary forms of characterizing visual properties for an effective and automated detection of image forgeries. We combine statistical telltales provided by different image descriptors that explore color, shape, and texture features. We focus on detecting image forgeries containing people and present a method for locating the forgery, specifically, the face of a person in an image. Experiments performed on three different open-access data sets show the potential of the proposed method for pinpointing image forgeries containing people. In the two first data sets (DSO-1 and DSI-1), the proposed method achieved a classification accuracy of 94% and 84%, respectively, a remarkable improvement when compared with the state-of-the-art methods. Finally, when evaluating the third data set comprising questioned images downloaded from the Internet, we also present a detailed analysis of target images.
Keywords Digital forensics
splicing detection
illuminant maps
image descriptors
machine learning
diversity measures
xmlui.dri2xhtml.METS-1.0.item-coverage Piscataway
Language English
Sponsor Coordination for the Improvement of Higher Education Personnel
Microsoft Research
CAPES DeepEyes Project
Sao Paulo Research Foundation
Brazilian National Research Council
Instituto Federal de Educacao, Ciencia e Tecnologia do Sudeste de Minas Gerais
University of Campinas
Grant number CAPES: 0214-13-2
FAPESP: 2010/05647-4
FAPESP: 2010/14910-0
FAPESP: 2011/22749-8
CNPq: 140916/2012-1
CNPq: 477662/2013-7
CNPq: 307113/2012-4
CNPq: 304352/2012-8
Date 2016
Published in Ieee Transactions On Information Forensics And Security. Piscataway, v. 11, n. 4, p. 720-733, 2016.
ISSN 1556-6013 (Sherpa/Romeo, impact factor)
Publisher Ieee-Inst Electrical Electronics Engineers Inc
Extent 720-733
Access rights Open access Open Access
Type Article
Web of Science ID WOS:000370734700005

Show full item record


Name: WOS000370734700005.pdf
Size: 4.357Mb
Format: PDF
Open file

This item appears in the following Collection(s)




My Account