An improved approach to detecting content-aware scaling-based tampering in JPEG images

Content-aware scaling is a method for image retargeting. It has been widely used in image manipulation including tampering. To improve the detection of the forgery in JPEG images, we propose to merge calibrated neighboring joint density and a rich models-based approach that was originally designed f...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE China Summit and International Conference on Signal and Information Processing pp. 432 - 436
Main Authors Qingzhong Liu, Cooper, Peter A., Bing Zhou
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2013
Subjects
Accuracy
calibrated neighboring joint density
content-aware scaling
Detectors
Discrete cosine transforms
Feature extraction
feature selection
forgery detection
Joints
JPEG
Mathematical model
rich model
Transform coding
Online AccessGet full text

Cover

More Information
Summary:Content-aware scaling is a method for image retargeting. It has been widely used in image manipulation including tampering. To improve the detection of the forgery in JPEG images, we propose to merge calibrated neighboring joint density and a rich models-based approach that was originally designed for steganalysis. A feature selection algorithm is utilized to reduce the feature dimensionality in the merged feature set. Experimental results show that the high-dimensional detector consisting of calibrated neighboring joint density and rich model features noticeably improves the detection accuracy; and the application of feature selection method to the high-dimensional detector can further improve the detection accuracy by using a much smaller and optimized feature set.
DOI:10.1109/ChinaSIP.2013.6625376