|
|||||
|
|
| 基于神经网络的图像盲水印技术 | |
| 引用本文： | 王忠,韵湘,孙钰.基于神经网络的图像盲水印技术[J].计算机工程与设计,2006,27(20):3858-3860. |
| 作者姓名： | 王忠 韵湘 孙钰 |
| 作者单位： | 1. 华中科技大学,光电子工程系,湖北,武汉,430074;武汉化工学院计算机科学与工程学院,湖北,武汉,430073 2. 烽火通信科技股份有限公司,湖北,武汉,430074 3. 武汉化工学院计算机科学与工程学院,湖北,武汉,430073 |
| 摘 要： | 将水印嵌入到宿主图像的小波变换域的低频分量;利用BP神经网络的自学习、自适应的特性和一段已知序列训练神经网络,根据确定的神经网络模型可实现水印的盲提取;在神经网络的输入信号计算上提出选择邻域窗口为3＊3方形窗口比十字窗口具有更好的实验效果.仿真实验结果表明该算法对常用的图像处理如JPEG压缩、剪切、加噪和滤波等攻击具有较好的鲁棒性和不可见性. |
| 关 键 词： | 数字水印 盲提取 神经网络 小波变换 鲁棒性 不可见性 |
| 文章编号： | 1000-7024（2006）20-3858-03 |
| 收稿时间： | 2005-08-23 |
| 修稿时间： | 2005-08-23 |
Blind watermark technology based on neural networks for image |
|
| WANG Zhong,YUN Xiang,SUN Yu.Blind watermark technology based on neural networks for image[J].Computer Engineering and Design,2006,27(20):3858-3860. | |
| Authors: | WANG Zhong YUN Xiang SUN Yu |
| Affiliation: | 1. Department of Optoelectronic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; 2. School of Computer Science and Engineering, Wuhan Institute of Chemical Technology, Wuhan 430073, China; 3. Fiberhome Telecommunication Technologies Limited Company, Wuhan 430074, China |
| Abstract: | The watermark is embedded the host image low-frequency coefficients based on wavelet transform.Using the self-learning and adaptive capabilities of neural network and a segment sequences can train the neural network.While the model of neural network is made certain,the blind watermark is extracted.The calculation of input sign show that selecting the 3*3 square window is better experi-mental effects than the cross window for calculating the input signals based on neural network.The experimental results show that the algorithm is robustness and imperceptibility against the original image process attacks such as JPEG compression,cropping,noise and filtering etc. |
| Keywords: | digital watermark blind extracting neural network wavelet transform robustness imperceptibility |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
