Detecting Shifted Double JPEG Compression Tampering Utilizing Both Intra-Block and Inter-Block Correlations

• Published in: Shanghai jiao tong da xue xue bao Vol. 18; no. 1; pp. 7 - 16
• Main Author: 张玉金 李生红 王士林
• Format: Journal Article
• Language: English
• Published: Heidelberg Shanghai Jiaotong University Press 01.02.2013
• Subjects: Architecture; Computer Science; DCT系数; Electrical Engineering; Engineering; JPEG压缩; JPEG图像; JPEG量化; Life Sciences; Materials Science; 二维数组; 修补程序; 离散余弦变换; 篡改检测; passive image forensics; shifted double JPEG (SDJPEG) compression; TP 391.4; copy-paste forgery; co-occurrence matrix; support vector machine (SVM)
• ISSN: 1007-1172; 1995-8188
• DOI: 10.1007/s12204-013-1362-9

Copy-paste forgery is a very common type of forgery in JPEG images. The tampered patch has always suffered from JPEG compression twice with inconsistent block segmentation. This phenomenon in JPEG image forgeries is called the shifted double JPEG （SDJPEG） compression. Detection of SDJPEG compressed image patches can make crucial contribution to detect and locate the tampered region. However, the existing SDJPEG compression tampering detection methods cannot achieve satisfactory results especially when the tampered region is small. In this paper, an effective SDJPEG compression tampering detection method utilizing both intra-block and inter-block correlations is proposed. Statistical artifacts are left by the SDJPEG compression among the magnitudes of JPEG quantized discrete cosine transform （DCT） coefficients. Firstly, difference 2D arrays, which describe the differences between the magnitudes of neighboring JPEG quantized DCT coefficients on the intra- block and inter-block, are used to enhance the SDJPEG compression artifacts. Then, the thresholding technique is used to deal with these difference 2D arrays for reducing computational cost. After that, co-occurrence matrix is used to model these difference 2D arrays so as to take advantage of second-order statistics. All elements of these co-occurrence matrices are served as features for SDJPEG compression tampering detection. Finally, support vector machine （SVM） classifier is employed to distinguish the SDJPEG compressed image patches from the single JPEG compressed image patches using the developed feature set. Experimental results demonstrate the efficiency of the proposed method.