基于小波包分解的图像信息隐写盲检测  

WPD-based blind image steganalysis

作　　者：罗向阳[1,2] 刘粉林[1] 王道顺[2] 

机构地区：[1]解放军信息工程大学信息工程学院,河南郑州450002 [2]清华大学计算机科学与技术系,北京100084

出　　处：《通信学报》2008年第10期173-182,共10页Journal on Communications

基　　金：国家高技术研究发展计划(“863”计划)基金资助项目(2006AA10Z409,2008AA10Z419);国家自然科学基金资助项目(60873249);河南省基础与前沿技术研究计划(082300410150)~~

摘　　要：基于小波包分解，提出了一类新的具有较高检测正确率的图像信息隐写盲检测方法。首先对图像进行小波包分解得到多个子带，从子带系数以及图像像素中提取直方图特征函数多阶绝对矩作为特征，然后对提取的特征进行预处理并设计BP神经网络分类器进行分类。针对LSB、SS、Jsteg、F5及MB等典型隐写的实验表明：此方法相比现有的典型盲检测方法，正确检测率提高约7．5％～17．2％，且具有更好的通用性。此外，还讨论了整数和非整数小波包分解对检测结果的影响。Based on wavelet package decomposition （WPD）, a new blind image steganalysis method was presented, which can detect the stego images with comparatively high accuracy. Firstly, by three scales of WPD, image was decom- posed into some coefficient subbands, and the multi-order absolute characteristic function moments of histogram were extracted as features from these subbands and image itself. And then, these features were processed and a back-propagation （BP） neural network was designed to classify original and stego images. A series of experiments were made to validate the performance of proposed method for five kinds of typical steganography methods, including LSB, SS, Jsteg, F5 and MB. Results show the method can detect stego and original images reliably, and the average detection accuracy of this method exceeds those of its closest competitors by at least 7.5% and up to 17.2%. Moreover, the influ- ence of integral and non-integral WPD for the detection accuracy was discussed.

关 键 词：信息隐写 盲检测 小波包分解 BP神经网络 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]