欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出一种基于独立分量分析ICA（Independent Component Analysis）的数字模型水印方法。嵌入水印时，对原始模型文件进行一级小波分解，在分解得到的逼近分量中利用随机混合方法嵌入水印后进行小波逆变换形成嵌入水印的模型文件。提取水印时，对模型文件进行一级小波分解，用基于最大峰值的ICA方法进行水印提取。仿真实验结果表明这种方法的强鲁棒性和可行性。这种方法可有效地保护模型的版权。
英文摘要：
A method of digital model watermarking based on Independent Component Analysis （ICA） is proposed in this paper. When embedding watermarking, the original model is decomposed by first-level discrete wavelet transform, the obtained approximation coefficient vector is embedded with watermarking by mixing randomly, and then the inverse transform is performed to reconstruct a model with embedded watermarking. When extracting watermarking, the model is decomposed by first-level discrete wavelet transform, and the watermarking is extracted by ICA based on kurtosis maximization. Emulated experiment results show that this method is robust and feasible. This method can protect the copyright of digital model effectively.
同期刊论文项目
同项目期刊论文
期刊信息
位置：