基于音频内容的DCT域脆弱水印算法  

Content-Based Fragile Audio Watermarking Algorithm in DCT Domain

作　　者：张金全[1,2] 王宏霞[1] 

机构地区：[1]西南交通大学信息科学与技术学院,四川成都610031 [2]成都信息工程学院网络工程学院,四川成都610225

出　　处：《西南交通大学学报》2012年第3期427-432,共6页Journal of Southwest Jiaotong University

基　　金：国家自然科学基金资助项目(61170226;60970122);中央高校基本科研业务费专项资金资助项目(SWJTU11CX047)

摘　　要：为了实现音频文件的完整性认证,提出了一种基于内容的脆弱水印算法.对于一维序列,改变其离散余弦变换(DCT)域交流系数不会改变该序列的幅值和.基于这一性质,在音频分帧后,再对每帧分组,计算每组采样点和的绝对值,相加后得到该帧的和,将其作为该帧音频的特征,量化后转换为二进制作为水印;然后,用量化索引调制方法,通过调整每组DCT域的低频系数嵌入水印.实验表明:该算法具有很好的不可感知性;得到的含水印音频的信噪比约为80 dB;算法对添加噪声、重量化、重采样、低通滤波、MP3压缩等操作具有很强的敏感性,并且能够确定替换等恶意篡改的位置.In order to realize the integrity authentication of audio files, a content-based fragile watermarking algorithm was proposed. To an one-dimensional sequence, the modification of ahemating coefficient in DCT （discrete cosine transformation） will not change the sum of the sequence. Based on this property, an audio signal is segmented into frames. Then, samples are partitioned into sections for each frame. After absolute value of the sum of all samples in each section is computed, all absolute values are added in a frame. The result is quantized as a feature of the frame, and the quantization result is converted to a binary sequence as watermark. The watermark bits are embedded by modifying low frequency coefficient in DCT of each section with the quantization index modulation （QIM） method. Experimental results show that the fragile watermarking algorithm maintains good perceptual quality, the SNR （signal-to-noise ratio ） values of watermarked audios are about 80 dB, and the algorithm is sensitive against additive noise, bit resolution transformation, sampling rate change, lowpass filtering and MP3 compression. Furthermore, it can detect and localize the tampered regions effectively.

关 键 词：音频水印 脆弱水印 量化索引调制 离散余弦变换(DCT) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]