JPEG steganalysis based on the entropy features of wavelet histogram distributions

被引：0

作者：

机构：

[1] School of Science, Naval University of Engineering, Wuhan

[2] Department of Information Security, Naval University of Engineering, Wuhan

来源：

Wu, Mingqiang | 1600年 / Binary Information Press卷 / 10期

基金：

中国国家自然科学基金;

关键词：

Histogram distribution; One-class classifier; Steganalysis; Symmetrical cross entropy; Wavelet coefficient;

D O I：

10.12733/jcis10807

中图分类号：

学科分类号：

摘要：

To detect the existence of hidden message in JPEG images, the histogram distributions of wavelet subbands are captured to describe the images statistical characteristics. And the symmetrical cross entropy difference features of the histogram distributions that captured from both detection images and their estimated cover images are calculated. Then a feature-matched one-class classifier is designed to make classification. Experimental results demonstrate that the proposed method can effectively distinguish between cover images and stego images, and significantly improves the detection accuracy. 1553-9105/Copyright © 2014 Binary Information Press

引用

页码：8139 / 8145

页数：6