Electronics, Communication & Automation Technology

Construction and Evaluation of Video Forgery Detection Database

Expand
  • School of Electronic and Information Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China
胡永健(1962-),男,博士,教授,主要从事多媒体信息取证、多媒体信息隐藏、图像处理、模式识别等研究.

Received date: 2017-02-17

  Revised date: 2017-03-14

  Online published: 2017-10-31

Supported by

Supported by the Science and Technology Planning Projects of Guangdong Province (2017A050501002) and the Sino-Singapore Joint Research Institute Projects(206-A017023)

Abstract

There has been a lack of standard video database for the research of video forgery detection.In order to solve this problem,a video forgery detection database (VFDD) is created.The database comprises 640 video clips,including the original videos captured by various imaging devices and the tampered videos created with the inter-frame and intra-frame manipulations.The details of the construction of the database are introduced.Four representative algorithms of video forgery detection in the literature are selected to perform a validity test on this da- tabase.The results show that the created database is capable of exhibiting the performance of different algorithms more comprehensively,which means that it is an effective evaluation database for video forgery detection algo- rithms.

Cite this article

HU Yong-jian SALMAN Al-hamidi WANG Yu-fei LIU Bei-bei LI Meng . Construction and Evaluation of Video Forgery Detection Database[J]. Journal of South China University of Technology(Natural Science), 2017 , 45(12) : 57 -64 . DOI: 10.3969/j.issn.1000-565X.2017.12.009

Outlines

/