基于ICA的数字模型水印研究  

ON DIGITAL MODEL OF WATERMARKING BASED ON INDEPENDENT COMPONENT ANALYSIS

作　　者：任平[1,2,3] 

机构地区：[1]解放军信息工程大学,河南郑州450002 [2]苏州市职业大学,江苏苏州215104 [3]苏州市数字城市工程研究中心,江苏苏州215000

出　　处：《计算机应用与软件》2009年第3期277-279,共3页Computer Applications and Software

基　　金：国家自然科学基金(10502026)

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。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.

关 键 词：数字模型水印 独立分量分析 离散小波变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP391.9[自动化与计算机技术—计算机科学与技术]