基于小波包与自适应预测器的音频隐写分析方法  

Audio steganalysis method based on wavelet packet and adaptive predictor

作　　者：王昱洁[1] 郭立[1] 王翠平[1] 丁治国[1] 

机构地区：[1]中国科学技术大学电子科学与技术系,合肥230027

出　　处：《中国科学院研究生院学报》2010年第1期49-54,共6页Journal of the Graduate School of the Chinese Academy of Sciences

基　　金：国家自然科学基金项目(60772032)资助

摘　　要：提出一种基于小波包与自适应预测器的音频隐写分析方法,主要用于检测加性噪声模型.利用加性噪声对音频高频部分比低频部分影响显著的特点,对音频信号进行小波包分解;然后利用最小均方(LMS)自适应预测器对高频小波包系数进行预测,选取预测误差的统计量作为统计特征;最后采用支持向量机分类.实验证明,对于常用的加性噪声隐写方法,即使在嵌入强度或嵌入率较低的情况下,也能达到较高的分类准确率.An audio steganalysis method based on wavelet packet and adaptive predictor is proposed. In this scheme,audio signals are firstly decomposed by the wavelet packet,the wavelet packet coefficients of high frequency are then predicted by the LMS adaptive predictor,statistics of predicted errors are selected as the statistical features,and finally SVM is implemented as a classifier. The experimental results verify that,for the commonly used steganography methods of additive noise,high classification accuracy can be achieved even in the case of low embedding strength or low embedding rate.

关 键 词：加性噪声模型 音频隐写分析 小波包分解 自适应预测 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]