结合重采样图像多分类的隐写分析算法

针对包含不同重采样图像和单次采样图像的混合异构图像进行隐写分析时,由于其统计特性的差异会造成隐写检测分类器中测试样本和训练样本的“失配”现象,从而降低隐写分析算法的检测性能.文章首先分析了不同插值算法和不同重采样因子的重采样图像作为训练样本和测试样本时,训练样本和测试样本“失配”对隐写分析的影响,随后构造了一种基于SVM的多分类器,用以对重采样图像进行多分类,最后提出了一种结合重采样图像多分类的隐写分析算法,降低了“失配”对隐写分析算法的影响,提高了混合异构图像环境下隐写分析算法的检测效果,并以LSBM隐写算法为例进行实验,实验结果验证了本算法的有效性.

Steganalysis Using Multi-Classification of Resized Images

When steganalysis is performed on hybrid heterogeneous images made up by different re- sampled images and raw single-sampled images, the difference in statistical properties can cause ＂mismatch＂ between training and testing images in the steganalytic classifier, thus decreasing the detection performance. This paper analyzes firstly the impact of different interpolation algorithms and scaling factors of resampling on steganalysis, as well as the impact of ＂mismatch＂ on steganalysis. Then a multi-classifier based on SVM is constructed to classify resized images into multiple catego- ries. Finally, a steganalytic method using multi-classification of resized images is presented. This method can reduce the mismatch penalty considerably, and increase the detection accuracy of the existing steganalytic methods under practical network environment. Experimental results validate the availability of the proposed method.