基于动态阈值的帧复制粘贴篡改检测①.PDFVIP

计 算 机 系 统 应 用 2016 年 第 25 卷 第 12 期 基于动态阈值的帧复制粘贴篡改检测① 卢贺楠 1,2,4, 黄添强 2,3,4, 林 晶 1,2,4 1(福建师范大学 数学与计算机科学学院, 福州 350007) 2(福建省公共服务大数据挖掘与应用工程技术研究中心, 福州 350007) 3(福建师范大学 软件学院, 福州 350007) 4(大数据分析与应用福建省高校工程研究中心, 福州 350007) 摘 要: 帧复制粘贴是一种常见的时域篡改方式, 篡改者采用这种方式来移除视频中某段内容, 如犯罪现场、犯 罪证据等. 针对这种篡改, 已经有不少方案被提出, 但是它们有两个缺点: 一采用固定的阈值; 二时间复杂度很 高. 大部分被篡改视频会经过再压缩处理, 由于视频压缩基本是有损压缩, 可能会导致固定阈值失去应有作用. 因此, 本文提出一种基于动态阈值的被动取证算法, 来增强算法的鲁棒性, 并且通过引入字典排序算法来缩小帧 匹配时的搜索范围, 成功降低了时间复杂度. 文章采用精确度、召回率和平均每帧计算时间来对提出算法的性能 进行评估, 结果表明本算法在这三方面都优于其他算法, 而且具有更好的鲁棒性. 关键词: 帧复制粘贴; 视频取证; 时域篡改; 动态阈值; 结构相识性系数 Frame Copy and Paste Tampering Detection Based on Dynamic Threshold LU He-Nan1,2,4, HUANG Tian-Qiang2,3,4, LIN Jing1,2,4 1(School of Mathematics and Computer Science, Fujian Normal University, Fuzhou 350007, China) 2(Fujian Engineering Research Center of Public Service Big Data Mining and Application, Fuzhou 350007, China) 3(School of Software, Fujian Normal University, Fuzhou 350007, China) 4(Fujian Provincial University Engineering Research Center of Big Data Analysis and Application, Fuzhou 350007, China) Abstract: Frame duplication forgery is a very common operation for video tampering in the temporal domain. By removing some frames which contain a crime scene or crime evidence, the forger can change the video content. A lot of solutions have been proposed for detecting this type of tempering operation. However, there are two disadvantages. The first one is fixed threshold; the other is huge computation. In general, frame duplication forgery and re-compression would be performed on a video at the same time. Since re-compression will cause data lost, the fixed thresholds may lose their effects. Therefore, an algorithm based on dynamic threshold is proposed in this paper, whi