基于纹理特征的数字视频篡改检测  

Digital Video Forgeries Detection Based on Textural Features

作　　者：袁秀娟[1] 黄添强[1,2] 陈智文[1] 吴铁浩[1] 苏立超[1] 

机构地区：[1]福建师范大学数学与计算机科学学院,福州350007 [2]福建师范大学网络安全与密码技术福建省高校重点实验室,福州350007

出　　处：《计算机系统应用》2012年第6期91-95,152,共6页Computer Systems & Applications

基　　金：国家自然科学基金(61070062);福建省自然科学基金(2008J04004);福建省高校服务海西建设重点项目(2008HX200941-4-5);福建省高等学校新世纪优秀人才支持计划(JA11038)

摘　　要：本文提出一种利用视频帧纹理特征来检测视频篡改的方法。对于一段背景静止或是运动缓慢连续变化的视频,相邻帧间的纹理特征相关性大,篡改后会一定程度上使其相关性变小,本文通过计算相邻帧灰度共生矩阵的相关性找出异常帧。该方法对视频格式无限制,适用于各种格式的视频。实验表明,该方法对相近背景下的异源帧插入、帧替换检测效果比较理想。This paper proposes a digital video tampering method which uses textural features of video frames. For a video with still background or slow and continuous movement, the correlation of interframe textural features is large and it would become smaller to some extent if tampered. This paper finds out the outliers according to the correlation of the interframe GLCM. This method is unlimited for video format, applied to any kind of video format. Experimental results show that this method can effectively detect video frame tampering including frame insertion and frame substitution of diverse-sourced in the similar background.

关 键 词：视频篡改 图像纹理 灰度共生矩阵 帧间相关性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]