By Topic

Blind Image Tampering Identification Based on Histogram Features

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Kaiwei Cai ; State Key Lab. of Digital Publishing Technol., Peking Univ., Beijing, China ; Xiaoqing Lu ; Jianguo Song ; Xiao Wang

Nowadays, digital forensics has emerged as an important research field with applications of authenticity/integrality verification for digital data. In this paper, we focus on image forensic techniques and propose a blind scheme for image tampering identification which is capable to determine the tampering type. Since tampering operations bring in changes to neighboring pixels, we suggest employing the difference image (the image composed of differences of adjacent pixels) for forensic analysis. More specifically, we take the histogram of difference image to construct a feature set, and then use these histogram features to train a Support Vector Machine(SVM) classifier. In this way, the novel scheme can efficiently identify usual image operations such as scaling, JPEG compression, linear and nonlinear filtering. Besides, its superiority over other state-of-the-art work is also demonstrated experimentally.

Published in:

Multimedia Information Networking and Security (MINES), 2011 Third International Conference on

Date of Conference:

4-6 Nov. 2011