摘要
基于分块级的模式噪声,提出一种基于最大似然估计的自适应阈值视频被动取证方法.它采用小波去噪和维纳滤波提取传感器的模式噪声,并通过固定大小的滑动窗口,计算分块级的能量梯度、信噪比和相邻帧相同位置块模式噪声的相关性构造特征值向量.在此基础上,采用最大似然估计得到判别篡改区域的自适应阈值.仿真实验结果表明,提出的方法对于复制-粘贴的视频内容篡改取得了较好的取证效果,并且能够对较小区域的篡改进行定位.
Based on the block-level sensor pattern noise （SPN）,a video forensics scheme,whose adaptive-threshold is obtained by maximum likelihood estimation,was proposed.It extracts the SPN by wavelet de-noising and Weiner filter.By setting a sliding window of fixed size,block-based energy gradient,signal-noise ratio and the correlation between the SPN of blocks with the same positions in neighboring frames are computed to build a feature vector.The maximum likelihood estimation is utilized to obtain the adaptive threshold of classification.Experiment results show that the proposed approach is effective for the forensics of copy-paste based tampering to the contents of digital video.Moreover,it can locate the tampering of small regions in digital video.
出处
《湖南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2013年第11期96-100,共5页
Journal of Hunan University:Natural Sciences
基金
国家自然科学基金资助项目(61072122
61379143)
教育部新世纪优秀人才计划资助项目(NCET-11-0134)
教育部高等学校博士学科点专项科研基金资助项目(20120161110014)
湖南省自然科学基金重点资助项目(11JJ2053)
关键词
视频被动取证
多特征向量
欧氏距离
最大似然估计
passive video forensics
multi-eigenvectors
Euclidean distance
maximum likelihood estimation
