English

应用科学学报 ›› 2013, Vol. 31 ›› Issue (1): 97-103.doi: 10.3969/j.issn.0255-8297.2013.01.016

• 信号与信息处理 • 上一篇    下一篇

基于图像内容和特征融合的隐写盲检测

李侃1,2， 平西建1   

  1. 1. 解放军信息工程大学信息工程学院，郑州450002
    2. 解放军西安通信学院军事电子工程系，西安710106
  • 收稿日期:2011-07-05 修回日期:2011-10-23 出版日期:2013-01-31 发布日期:2011-09-23
  • 作者简介:平西建，教授，博导，研究方向：图像处理、模式识别、信息隐藏，E-mail：pingxijian@yahoo.com.cn
  • 基金资助:

    国家自然科学基金（No.60970142）资助

Blind Steganalysis Based on Image Content and Feature Fusion

LI Kan1,2, PING Xi-jian1   

  1. 1. Institute of Information Engineering, PLA Information Engineering University, Zhengzhou 450002, China
    2. Faculty of Automation and Information Engineering, PLA Xi’an Communication Institute, Xi’an 710106, China
  • Received:2011-07-05 Revised:2011-10-23 Online:2013-01-31 Published:2011-09-23

PDF

1575

被引次数

1

摘要： 随着特征选择和分类技术研究的不断深入，盲检测的精度越来越高，但现有方法大多不考虑图像自身的内容特性对检测的影响. 该文提出一种基于图像内容和特征融合的盲检测方法，根据图像复杂度将待检测图像划分为不同的子图像库，以巴氏距离度量各局部特征的分类能力并确定权值，在特征融合基础上对各子库提取不同特征，用支持向量机进行分类. 在混合图像库上进行的实验表明，该方法具有更好的检测性能，并降低了运算复杂度.

关键词: 隐写分析, 图像内容, 特征融合, 巴氏距离

Abstract: With increasing research on image feature vector extraction and classification, blind steganalysis is becoming more efficient and accurate. However, many existing methods use similar processing for all images without taking account the diverse image contents. This paper proposes a new approach based on
image contents and feature fusion. The input images are divided into several classes according to the content complexity before feature extraction. Bhattacharyya distance is used to evaluate the usefulness of individual features and determine their weights. Steganalysis is subsequently conducted using a fusing approach and a support vector machine (SVM) classifier in a decision making process. Experimental results on several sets of  images demonstrate that the proposed steganalyzer outperforms some previous methods. It provides reliable results with reduced computational complexity.

Key words: steganalysis, image content, feature fusion, Bhattacharyya distance

中图分类号: