Digital image splicing detection based on Markov features in DCT and DWT domain

被引:237
作者
He, Zhongwei [2 ]
Lu, Wei [1 ]
Sun, Wei [2 ]
Huang, Jiwu [1 ]
机构
[1] Sun Yat Sen Univ, Sch Informat Sci & Technol, Guangdong Key Lab Informat Secur Technol, Guangzhou 510006, Guangdong, Peoples R China
[2] Sun Yat Sen Univ, Sch Software, Guangzhou 510006, Guangdong, Peoples R China
基金
中国国家自然科学基金;
关键词
Image splicing detection; Digital image forensics; Discrete cosine transform; Discrete wavelet transform; Markov; SVM-RFE; TRANSFORM;
D O I
10.1016/j.patcog.2012.05.014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Image splicing is very common and fundamental in image tampering. To recover people's trust in digital images, the detection of image splicing is in great need. In this paper, a Markov based approach is proposed to detect this specific artifact. Firstly, the original Markov features generated from the transition probability matrices in DCT domain by Shi et al. is expanded to capture not only the intrablock but also the inter-block correlation between block DCT coefficients. Then, more features are constructed in DWT domain to characterize the three kinds of dependency among wavelet coefficients across positions, scales and orientations. After that, feature selection method SVM-RFE is used to fulfill the task of feature reduction, making the computational cost more manageable. Finally, support vector machine (SVM) is exploited to classify the authentic and spliced images using the final dimensionality-reduced feature vector. The experiment results demonstrate that the proposed approach can outperform some state-of-the-art methods. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:4292 / 4299
页数:8
相关论文
共 33 条
[1]   A SIFT-Based Forensic Method for Copy-Move Attack Detection and Transformation Recovery [J].
Amerini, Irene ;
Ballan, Lamberto ;
Caldelli, Roberto ;
Del Bimbo, Alberto ;
Serra, Giuseppe .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2011, 6 (03) :1099-1110
[2]  
[Anonymous], 2003, 2003 C COMPUTER VISI, DOI [DOI 10.1109/CVPRW.2003.10093.27.T.-T, DOI 10.1109/CVPRW.2003.10093]
[3]  
[Anonymous], P INF SEC SOL EUR BE
[4]  
[Anonymous], 2004, 20320043 COL U
[5]  
Chang C., 2010, LIBSVM: A library for support vector machines 2010
[6]   JPEG image steganalysis utilizing both intrablock and interblock correlations [J].
Chen, Chunhua ;
Shi, Yun Q. .
PROCEEDINGS OF 2008 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-10, 2008, :3029-3032
[7]  
Chen W., 2007, IMAGING SECURITY STE
[8]  
Dong J, 2009, LECT NOTES COMPUT SC, V5450, P76, DOI 10.1007/978-3-642-04438-0_7
[9]  
Dong J, 2008, LECT NOTES COMPUT SC, V5041, P87
[10]  
Dong Jing., 2011, CASIA TAMPERED IMAGE