|Table of Contents|

[1] Wang Zhenfei, Song Shengli,. Digital watermarking algorithmbased on neural network in multiwavelet domain [J]. Journal of Southeast University (English Edition), 2007, 23 (2): 211-215. [doi:10.3969/j.issn.1003-7985.2007.02.012]
Copy

Digital watermarking algorithmbased on neural network in multiwavelet domain()
基于神经网络和多小波变换的数字水印算法
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
23
Issue:
2007 2
Page:
211-215
Research Field:
Computer Science and Engineering
Publishing date:
2007-06-30

Info

Title:
Digital watermarking algorithmbased on neural network in multiwavelet domain
基于神经网络和多小波变换的数字水印算法
Author(s):
Wang Zhenfei1 2 Song Shengli3
1College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
2 College of Information Engineering, Zhengzhou University, Zhengzhou 450001, China
3Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
王振飞1 2 宋胜利3
1 华中科技大学计算机科学与技术学院, 武汉 430074; 2 郑州大学信息工程学院, 郑州 450001; 3 华中科技大学控制科学与工程系, 武汉 430074
Keywords:
digital watermarking neural networks multiwavelet transform
数字水印 神经网络 多小波变换
PACS:
TP391
DOI:
10.3969/j.issn.1003-7985.2007.02.012
Abstract:
A novel blind digital watermarking algorithm based on neural networks and multiwavelet transform is presented.The host image is decomposed through multiwavelet transform.There are four subblocks in the LL-level of the multiwavelet domain and these subblocks have many similarities.Watermark bits are added to low-frequency coefficients.Because of the learning and adaptive capabilities of neural networks, the trained neural networks almost exactly recover the watermark from the watermarked image.Experimental results demonstrate that the new algorithm is robust against a variety of attacks, especially, the watermark extraction does not require the original image.
基于图像多小波域低频系数子块的相似性, 利用神经网络的学习特性, 提出了新的盲数字水印算法.将宿主图像变化为多小波域, 把水印加入到宿主图像多小波变化后的低频系数中.通过后向传播算法的神经网络训练出宿主图像与嵌入的水印信号之间的关系特征, 利用神经网络具有学习和自适应的特性, 训练后的神经网络能够完全恢复嵌入到宿主图像中的水印信息.仿真实验表明, 该算法针对各种攻击具有很好的鲁棒性, 特别是在水印检测时不需要原始图像.

References:

[1] Liu Jiang-Lung, Lou Der-Chyuan, Chang Ming-Chang, et al.A robust watermarking scheme using self-reference image[J].Computer Standards & Interfaces, 2006, 28(3): 356-367.
[2] Celik M U, Sharma G, Tekalp A M, et al.Lossless generalized-LSB data embedding[J].IEEE Transactions on Image Processing, 2005, 14(2):253-266.
[3] Cox I J, Kilian J, Leighton T, et al.Secure spread spectrum watermarking for multimedia[J].IEEE Transactions on Image Processing, 1997, 6(12):1673-1687.
[4] Dietl W, Meerwald P, Uhl A.Protection of wavelet-based watermarking systems using filter parameterization[J].Signal Processing, 2003, 83(10):2095-2116.
[5] Wang Shih-Hao, Lin Yuan-Pei.Wavelet tree quantization for copyright protection watermarking[J].IEEE Transactions on Image Process, 2004, 13(2):154-165.
[6] Reddy A A, Chatterji B N.A new wavelet based logo-watermarking scheme[J].Pattern Recognition Letters, 2005, 26(7):1019-1027.
[7] Ghouti L, Bouridane A, Ibrahim M K, et al.Digital image watermarking using balanced multiwavelets[J].IEEE Transactions on Signal Processing, 2006, 54(4):1519-1536.
[8] Yu Pao-Ta, Tsai Hung-Hsn, Lin Jyh-Shyan.Digital watermarking based on neural networks for color images[J].Signal Processing, 2001, 81(3):663-671.
[9] Kutter M, Jordan F, Bossen F.Digital watermarking of color images using amplitude modulation[J].Journal of Electronic Image, 1998, 7(2):326-332.
[10] Geronimo J S, Hardin D P, Massopust P R.Fractal functions and wavelet expansions based on several functions[J].Journal of Approximation Theory, 1994, 78(3):373-401.

Memo

Memo:
Biography: Wang Zhenfei(1973—), male, doctor, associate professor, wzfei@zzu.edu.cn.
Last Update: 2007-06-20