Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (28): 178-182.

Previous Articles     Next Articles

Image steganalysis based on wavelet coefficient dependencies

XU Pan1, SU Guangwei2   

  1. 1.Department of Communication Engineering, Engineering University of the Chinese Armed Police Force, Xi’an 710086, China
    2.Key Laboratory of Network & Information Security under the Chinese Armed Police Force, Department of Electronic Technology, Engineering University of the Chinese Armed Police Force, Xi’an 710086, China
  • Online:2012-10-01 Published:2012-09-29

基于小波系数相关性的图像隐写分析

徐  攀1,苏光伟2   

  1. 1.武警工程大学 通信工程系,西安 710086
    2.武警工程大学 电子技术系 网络与信息安全武警部队重点实验室,西安 710086

Abstract: In the paper, a new image steganalysis technique using wavelet packet decomposition and wavelet coefficient dependencies is proposed. It decomposes the preprocessing image using wavelet packet decomposition and extracts the higher-order statistics of the image and its wavelet packet sub bands as features. It exploits the scale and orientation dependencies between wavelet coefficients and extracts intrascale and interscale features using Markov matrices. The experiments on H4PGP, F5 and OutGuess steganography show the method can detect stego images reliably.

Key words: steganalysis, wavelet packet decomposition, wavelet coefficient dependency

摘要: 提出了一种基于小波包分解和小波系数相关性的通用型图像隐写分析方法。对差分处理后的图像进行小波包分解,提取图像及其小波子带的高阶统计量作为特征。利用图像小波系数在尺度方向和空间方向的相关性,使用马尔可夫模型挖掘小波系数层内和层间相关性,提取转移概率矩阵作为特征。针对H4PGP、F5和OutGuess隐写算法的实验表明,方法对上述三种隐写算法具有较好的检测效果。

关键词: 隐写分析, 小波包分解, 小波系数相关性