A machine learning based scheme for double JPEG compression detection
A machine learning based scheme for double JPEG compression detection
复制标题
DOI：
10.1109/icpr.2008.4761645
复制
发表时间：
2008-12
期刊：
影响因子：
--
通讯作者：
Chunhua Chen;Y. Shi;W. Su
中科院分区：
文献类型：
--
作者：
Chunhua Chen;Y. Shi;W. Su
双重JPEG压缩检测在数字取证中具有重要意义。我们提出了一个有效的基于机器学习的方案来区分双重和单一的JPEG压缩图像。首先，差分JPEG 2D阵列，即，利用JPEG系数二维阵列的大小与其沿着不同方向的移位版本之间的差异来增强双重JPEG压缩伪影。马尔可夫随机过程，然后应用到建模的差异2-D阵列，以便利用二阶统计量。此外，阈值技术被用来减少转移概率矩阵的大小，它表征马尔可夫随机过程。这些矩阵的所有元素被收集作为双重JPEG压缩检测的特征。采用支持向量机作为分类器。实验表明，我们提出的方案优于现有技术。
Double JPEG compression detection is of significance in digital forensics. We propose an effective machine learning based scheme to distinguish between double and single JPEG compressed images. Firstly, difference JPEG 2D arrays, i.e., the difference between the magnitude of JPEG coefficient 2D array of a given JPEG image and its shifted versions along various directions, are used to enhance double JPEG compression artifacts. Markov random process is then applied to modeling difference 2-D arrays so as to utilize the second-order statistics. In addition, a thresholding technique is used to reduce the size of the transition probability matrices, which characterize the Markov random processes. All elements of these matrices are collected as features for double JPEG compression detection. The support vector machine is employed as the classifier. Experiments have demonstrated that our proposed scheme has outperformed the prior arts.