Forensic Methods for Detecting Image Manipulation - Copy Move

Anthony Sutardja, Omar Ramadan and Yan Zhao

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2015-84
May 13, 2015

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-84.pdf

For the past century, photographs have served as reliable primary sources of evidence, but that is quickly changing. Photo manipulation tools have become widespread and it is easy to manipulate images. Photo manipulations tools such as Adobe PhotoShop afford greater artistic expression, and enable users to create manipulations that challenge the limits of our natural perception. The difference between authentic and manipulated photos has become harder to distinguish, and can only be detected by digital forensic experts. The image forensics capstone project aims to create an online software service that performs the work of forensic analysts, and visualizes and analyzes the possible manipulations that may have been performed on an image. Our goal is to empower anybody to perform image forensic analysis, and help increase our faith in digital content. Our capstone team has researched several image manipulation detection techniques including copy-move detection, higher order statistics, error level analysis, and JPEG double compression analysis. We have also completed a prototype of this image manipulation detection web service that helps a user identify fraudulent features within an image.

Advisor: James O'Brien


BibTeX citation:

@mastersthesis{Sutardja:EECS-2015-84,
    Author = {Sutardja, Anthony and Ramadan, Omar and Zhao, Yan},
    Title = {Forensic Methods for Detecting Image Manipulation - Copy Move},
    School = {EECS Department, University of California, Berkeley},
    Year = {2015},
    Month = {May},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-84.html},
    Number = {UCB/EECS-2015-84},
    Abstract = {For the past century, photographs have served as reliable primary sources of evidence, but that is quickly changing. Photo manipulation tools have become widespread and it is easy to manipulate images. Photo manipulations tools such as Adobe PhotoShop afford greater artistic expression, and enable users to create manipulations that challenge the limits of our natural perception. The difference between authentic and manipulated photos has become harder to distinguish, and can only be detected by digital forensic experts. The image forensics capstone project aims to create an online software service that performs the work of forensic analysts, and visualizes and analyzes the possible manipulations that may have been performed on an image. Our goal is to empower anybody to perform image forensic analysis, and help increase our faith in digital content.
Our capstone team has researched several image manipulation detection techniques including copy-move detection, higher order statistics, error level analysis, and JPEG double compression analysis. We have also completed a prototype of this image manipulation detection web service that helps a user identify fraudulent features within an image.}
}

EndNote citation:

%0 Thesis
%A Sutardja, Anthony
%A Ramadan, Omar
%A Zhao, Yan
%T Forensic Methods for Detecting Image Manipulation - Copy Move
%I EECS Department, University of California, Berkeley
%D 2015
%8 May 13
%@ UCB/EECS-2015-84
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-84.html
%F Sutardja:EECS-2015-84