| 基于高斯混合模型的DCT域水印检测方法 |
| |
| 引用本文： | 林晓丹.基于高斯混合模型的DCT域水印检测方法[J].自动化学报,2012,38(9):1445-1448. |
| |
| 作者姓名： | 林晓丹 |
| |
| 作者单位： | 1.华侨大学信息科学与工程学院 厦门 361021 |
| |
| 基金项目： | 泉州市科技计划项目(2011G7)资助~~ |
| |
| 摘 要： | 基于音频DCT系数的统计特征,提出了一种水印检测方法.采用扩频的方法在DCT域嵌入水印, 分别对嵌入水印和未包含水印的音频信号在DCT域进行统计学习,得到对应的高斯混合模型(Gaussian mixture model, GMM). 接收端采用最大似然检测,判断是否嵌入水印并提取相应的水印信息. 仿真结果表明本文的水印检测算法对常见的信号攻击具有鲁棒性,与传统的相关检测法相比,检测可靠性更高.
|
| 关 键 词： | 水印检测 DCT域 高斯混合模型 最大似然 |
| 收稿时间： | 2011-7-28 |
| 修稿时间： | 2011-11-10 |
DCT-domain Watermark Detection Using Gaussian Mixture Model |
| |
| LIN Xiao-Dan.DCT-domain Watermark Detection Using Gaussian Mixture Model[J].Acta Automatica Sinica,2012,38(9):1445-1448. |
| |
| Authors: | LIN Xiao-Dan |
| |
| Affiliation: | 1.College of Information Science and Engineering, Huaqiao University, Xiamen 361021 |
| |
| Abstract: | An audio watermark detector is developed based on the statistical characteristics of audio in DCT domain. Watermarks are embedded in DCT domain on a spread spectrum basis. A Gaussian mixture model (GMM) is introduced to model both the watermarked and unwatermarked audio signals in DCT domain. At the receiver a maximum likelihood detector is employed. Simulation results indicate that the proposed method allows for common signal processing and provides a better detecting accuracy compared with the linear correlation detector. |
| |
| Keywords: | Watermark detection DCT domain Gaussian mixture model (GMM) maximum likelihood |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
