基于混沌映射的视频数字水印算法  

Novel Video Watermarking Algorithm Based on MPEG-7 Contour Description

作　　者：马洁[1] 李建福[2] 

机构地区：[1]重庆教育学院学生处,重庆400067 [2]重庆教育学院计算机科学系,重庆400067

出　　处：《计算机科学》2010年第9期287-289,F0003,共4页Computer Science

基　　金：重庆市教委项目(No.kj091502)资助

摘　　要：为了更好地保护视频数据的版权,提出了一种基于混沌映射的视频水印算法。在该算法中,原始视频数据被分割成等帧数的视频组,利用MPEG-7的轮廓编码计算每个视频帧的主要物体轮廓坐标点集合;然后通过傅立叶变换得到该帧轮廓点形状不变量,利用哈希的方法计算水印信号和这些不变量的有效值作为密钥之一;再对整个视频组的轮廓点进行傅立叶变换,得到其时间轴上的有效不变域,并将水印信号嵌入在这个不变域的中频部分,采用混沌技术,提高了水印的嵌入量和算法的鲁棒性。在水印提取阶段,通过对水印的多重校验,确保水印信号的可靠性。实验结果表明,该算法对大部分的视频攻击都具有良好的鲁棒性。For the copyright protection of digital video,a novel video watermarking algorithm based on MPEG-7 contour description was proposed.The original video is spitted into a series of frame groups,for each frame in the group,the points of contour shape are described by MPEG-7,and taking advantage of hash function to calculate the Keys between those points in the 1D-DFT transform domain and the watermark signals.Then,decomposes all those contour points of each frame in one group through 2D-DFT transform and obtains the invariant domain of the time axis and the contours,and then embeds the watermark signals into this domain to ensure the watermark reliability and robustness.And in the process of watermark extracting,it is performed multiple watermark verification to keep it accuracy.Experimental results show that the watermarked frames are indistinguishable from the original frames subjectively and the proposed video watermarking algorithm is robust against the attacks of additive Gaussian noise,frame dropping,frame averaging and lossy compression.

关 键 词：视频水印 混沌映射 傅立叶变换 MPEG-7 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]