| Rotation, Scaling and Translation Invariant Blind Image Watermarking Scheme Utilizing Zernike Moments |
| |
| 作者姓名： | 吴健珍 谢剑英 |
| |
| 作者单位： | Dept. of automation, Shanghai Jiaotong University, Shanghai 200030 |
| |
| 基金项目： | Acknowledgements The first author would like to express her deep appreciation to postgraduate Mr. Yang Jinghui in Northeastern University for fruitful discussions and suggestions. |
| |
| 摘 要： | A novel adaptive blind image watermarking scheme resistant to Rotation, scaling and translation （RST） attacks is proposed in this paper. Based on fuzzy clustering theory and Human visual system （HVS） model, the spread spectrum watermark is adaptively embedded in Discrete wavelet transform （DWT） domain. In order to register RST transform parameters, a hierarchical neural network is utilized to learn image geometric pattern represented by low order Zernike moments. Watermark extraction is carried out after watermarked image has been synchronized without original image. It only needs a trained neural network. Experiments show that it can embed more robust watermark under certain visual distance, effectively resist Joint photographic experts group （JPEG） compression, noise and RST attacks.
|
| 关 键 词： | 数字水印 RST攻击 泽尔尼克矩 分层神经网络 图象处理 |
| 收稿时间： | 2004-10-15 |
Rotation, Scaling and Translation Invariant Blind Image Watermarking Scheme Utilizing Zernike Moments |
| |
| WU Jian-zhen,XIE Jian-ying.Rotation, Scaling and Translation Invariant Blind Image Watermarking Scheme Utilizing Zernike Moments[J].Journal of Donghua University,2005,22(5):53-58. |
| |
| Authors: | WU Jian-zhen XIE Jian-ying |
| |
| Abstract: | A novel adaptive blind image watermarking scheme resistant to Rotation , scaling and translation (RST) attacks is proposed in this paper. Based on fuzzy clustering theory and Human visual system (HVS) model, the spread spectrum watermark is adaptively embedded in Discrete wavelet transform (DWT) domain. In order to register RST transform parameters, a hierarchical neural network is utilized to leam image geometric pattern represented by low order Zernike moments. Watermark extraction is carried out after watermarked image has been synchronized without original image. It only needs a trained neural network. Experiments show that it can embed more robust watermark under certain visual distance, effectively resist Joint photographic experts group (JPEG) compression, noise and RST attacks. |
| |
| Keywords: | digital watermarking RST attacks Zernike moments hierarchical neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
