基于帧化采样和小波HMM的三维模型信息隐藏  

Steganography for 3D Model Based on Frame Transform and HMM Model in Wavelet Domain

作　　者：綦科[1,2] 张大方[1] 谢冬青[2] 

机构地区：[1]湖南大学计算机与通信学院,长沙410082 [2]广州大学计算机科学与教育软件学院,广州510006

出　　处：《计算机辅助设计与图形学学报》2010年第8期1406-1411,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(60673156);广东省自然科学基金(8151007101000021;9151009001000059)

摘　　要：针对现有三维模型变换域信息隐藏容量小、严格依赖顶点排列顺序及拓扑结构、只适用于规则或半规则等特定三维模型的不足,将视频流方法引入三维模型的信息隐藏,提出一种基于帧化采样的小波域信息隐藏算法.通过设计等高线空间分割和帧化采样,应用小波域隐马尔可夫模型(HMM)实现了小波系数零树结构信息隐藏;扩展了基于视觉系统小波域量化噪声的视觉权重分析方法,以自适应地确定信息隐藏的强度.实验结果表明,该算法具有高嵌入量(每个顶点嵌入3比特)、高安全性和低失真度的优点,能够抵抗仿射变换攻击和顶点重排攻击,适合任意网格的三维模型信息隐藏.Steganography for 3D model in transform domain has deficiency of low capacity, strict dependency on vertex order or topological structure, and is only suitable for regular or half-regular mesh. A steganography for 3D model based on frame transform is proposed in which contour space subdivision and frame transform are designed to map 3D data to frame data. The hidden Markov model （HMM） in wavelet domain is applied to embed data in the zero-tree structure of HMM. The just noticeable distortion analysis based on the human visual system is expanded and applied to the 3D data. The experimental results have shown that the proposed method has features of high security, high capacity （3 bits per vertex） and low distortion, is robust against affine transformation and vertex reordering attack, and is suitable for any meshes of 3D model.

关 键 词：信息隐藏 三维模型 帧化采样 小波HMM 等高线空间分割 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]