Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (20): 37-39.

• 学术探讨 • Previous Articles     Next Articles

Genetic algorithm and one-class support vector machines for image steganography detection

GUO Xuan1,YANG Xiao-yuan1,2,LIU Jia1,HAN Peng1   

  1. 1.Network and Information Security Key Laboratory,Electronics Department of Engineering College of the APF,Xi’an 710086,China
    2.National Key Laboratory on ISN,Xidian University,Xi’an 710071,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-11 Published:2007-07-11
  • Contact: GUO Xuan

基于遗传算法和一类SVM的隐秘图像检测方案

郭 璇1,杨晓元1,2,刘 佳1,韩 鹏1   

  1. 1.武警工程学院 电子技术系网络与信息安全武警部队重点实验室,西安 710086
    2.西安电子科技大学 ISN国家重点实验室,西安 710071
  • 通讯作者: 郭 璇

Abstract: This paper brings forward a new detection of steganography method based on genetic algorithms and one-class SVM.We apply genetic algorithm to search out and identify the potential informative features combinations for classification,and then use the classification accuracy from the support vector machine classifier to determine the fitness in genetic algorithm.Experiment results show its better performance in the efficiency of detecting system.

Key words: image steganography detection, feature selection, genetic algorithm, one-class support vector machines

摘要: 针对二类支持向量机分类器在隐秘图像检测中训练步骤复杂与推广性弱的缺点,提出了一种新的基于遗传算法和一类支持向量机的隐秘图像检测方案。采用遗传算法进行图像特征选择,一类支持向量机作为分类器。实验结果表明,与只利用一类支持向量机分类,但未进行特征选择的隐秘检测方法相比,提高了隐秘图像检测的识别率和系统检测效率。

关键词: 隐秘图像检测, 特征选择, 遗传算法, 一类支持向量机