作者: Zhenzhen Zhang , Jianjun Hou , Qinglong Ma , Zhaohong Li
DOI: 10.1002/SEC.981
关键词:
摘要: Frame insertion and deletion are common inter-frame forgery in digital videos. In this paper, an efficient method based on quotients of correlation coefficients between local binary patterns LBPs coded frames is proposed. This composed two parts: feature extraction abnormal point detection. the extraction, each frame a video by LBP. Then, among sequential LBP-coded calculated. detection, localization achieved using Tchebyshev inequality twice followed points detection decision-thresholding. Experimental results show that our has high accuracy low computational complexity. Copyright © 2014 John Wiley & Sons, Ltd.