一种基于粗糙集属性约简的图像隐藏信息检测方法  

Steganalysis Based on the Rough Set Attribute Reduction

作　　者：戴蒙[1] 林家骏[1] 毛家发[1] 

机构地区：[1]华东理工大学信息科学与工程学院

出　　处：《华东理工大学学报（自然科学版）》2008年第1期122-125,共4页Journal of East China University of Science and Technology

摘　　要：基于统计分析的检测方法是图像隐藏信息检测常用的方法,与特定隐写分析方法相比,它比较灵活,能够快速地适应新的或未知的隐写算法。针对特征属性高维的特点,采用粗糙集属性约简的方法来降低数据规模。实验表明:与采用全部属性的检测系统相比,该方法在不影响分类精度的前提下有效提高了检测速度。The statistical detection is generally used in steganalysis. Comparing with the special stega- nalysis, it has the advantage of flexing. However, it has the disadvantages in large-scale data,and low calculate speed. For the high dimensions of feature attributes, the attributes reduction based on rough set can delete the non-important knowledge while not alter the classification ability of knowledge. The result of experiment shows that the proposed detection technique achieves a comparable precise detection rate as algorithm based on all feature attributes, however, it evidently decreases detection time.

关 键 词：隐写术 隐写分析 粗糙集 属性约简 

分 类 号：TN918.91[电子电信—通信与信息系统]