摘要
针对扩频水印的盲提取问题,提出了一种在数字音频中扩频水印的盲提取算法。算法将扩频后的水印信息隐藏在音频文件小波分解的低频系数再做离散余弦变换(DCT)后的第5个系数中。提取时在扩频序列及其长度均未知的情况下,采用二次谱和奇异值分解(SVD)的方法对嵌入时使用的扩频参数进行估计,实现了数字音频中扩频水印的盲提取。仿真实验表明,所提算法在未知扩频参数的情况下能提取出归一化系数(NC)为1的水印图像并且水印的鲁棒性也很强,在加噪、低通滤波等攻击下估计出的扩频序列正确率能达到90%以上,恢复出的水印图像清晰可见,归一化系数都在0.98以上。
According to the blind extracting issues within the spread-spectrum watermark, a kind of blind extracting algorithm which could be used in the extraction of the digital audio signals was proposed. In the algorithm, wavelet transform was applied to the audio document, then the Discrete Cosine Transform （DCT） was used to its low-frequency coefficient. Afterwards, the fifth coefficient was got and it was used to hide the watermark information being spectrum spread. As the spread-spectrum sequence and its length were unknown during the extraction, spectrum-reprocessing and Singular Value Decomposition （SVD） were introduced to estimate the spread-spectrum using in the embedding process, and the blind extraction to the spread-spectrum watermark of the given digital signal was fulfilled. The simulation results show that with unknown spread-spectrum parameter, watermark image with Normalized Coefficient （NC） of one can be extracted, and it is of strong robustness. Under the attacks of noises and low-pass filter, the accuracy rate of the estimating spread-spectrum sequence is over 90%, which guarantees the recovery of clear water mark image with normalization coefficient higher than 0. 98.
出处
《计算机应用》
CSCD
北大核心
2013年第1期138-141,145,共5页
journal of Computer Applications
基金
国家自然科学基金资助项目(61071196
61102131)
教育部新世纪优秀人才支持计划项目(NCET-10-0927)
信号与信息处理重庆市市级重点实验室建设项目(CSTC2009CA2003)
重庆市杰出青年基金资助项目(CSTC2011jjjq40002)
重庆市自然科学基金资助项目(CSTC2009BB2287
CSTC2010BB2398
CSTC2010BB2409
CSTC2010BB2411)
关键词
离散小波变换
离散余弦变换
扩频水印
扩频序列
二次谱
奇异值分解
Discrete Wavelet Transform （DWT）
Discrete Cosine Transform （DCT）
spread-spectrum watermark
spread-spectrum sequence
spectrum-reprocessing
Singular Value Decomposition （SVD）
