TY - JOUR
T1 - Detecting median filtering via two-dimensional AR models of multiple filtered residuals
AU - Yang, Jianquan
AU - Ren, Honglei
AU - Zhu, Guopu
AU - Huang, Jiwu
AU - Shi, Yun Qing
N1 - Funding Information:
The authors appreciate the anonymous reviewers for their constructive comments. This work was supported in part by the National Natural Science Foundation of China under Grant 61572489 and Grant 61672554, and in part by the Youth Innovation Promotion Association of CAS under Grant 2015299.
Publisher Copyright:
© 2017, Springer Science+Business Media New York.
PY - 2018/4/1
Y1 - 2018/4/1
N2 - Median filtering, being an order statistic filtering, has been widely used in image denoising and recently also in image anti-forensics and anti-steganalysis. In the past few years, several methods have been developed for median filtering detection. However, it is still a challenging task to detect median filtering in JPEG compressed images. In this paper, we propose a novel method to solve this challenging task. We first generate median filtered residual (MFR), average filtered residual (AFR) and Gaussian filtered residual (GFR) by calculating the differences between an original image and its filtered images. Then, we propose to use two-dimensional autoregressive (2D-AR) model to characterize MFR, AFR and GFR separately, and further combine the 2D-AR coefficients of these three residuals into a set of features. Finally, the extracted feature set is fed into a support vector machine classifier for training and detection. Extensive experiments have demonstrated that compared with existing methods, the proposed one can achieve a considerable improvement in detecting median filtering in heavily compressed images.
AB - Median filtering, being an order statistic filtering, has been widely used in image denoising and recently also in image anti-forensics and anti-steganalysis. In the past few years, several methods have been developed for median filtering detection. However, it is still a challenging task to detect median filtering in JPEG compressed images. In this paper, we propose a novel method to solve this challenging task. We first generate median filtered residual (MFR), average filtered residual (AFR) and Gaussian filtered residual (GFR) by calculating the differences between an original image and its filtered images. Then, we propose to use two-dimensional autoregressive (2D-AR) model to characterize MFR, AFR and GFR separately, and further combine the 2D-AR coefficients of these three residuals into a set of features. Finally, the extracted feature set is fed into a support vector machine classifier for training and detection. Extensive experiments have demonstrated that compared with existing methods, the proposed one can achieve a considerable improvement in detecting median filtering in heavily compressed images.
KW - Autoregressive (AR) model
KW - Filtered residual
KW - Image forensics
KW - Median filtering detection
UR - http://www.scopus.com/inward/record.url?scp=85017633568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85017633568&partnerID=8YFLogxK
U2 - 10.1007/s11042-017-4691-0
DO - 10.1007/s11042-017-4691-0
M3 - Article
AN - SCOPUS:85017633568
SN - 1380-7501
VL - 77
SP - 7931
EP - 7953
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 7
ER -