Open AccessFrame duplication/mirroring detection method with binary features
Author(s) -
Ulutas Guzin,
Ustubioglu Beste,
Ulutas Mustafa,
Nabiyev Vasif
Publication year - 2017
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2016.0321
Subject(s) - mirroring , computer science , frame (networking) , artificial intelligence , computer vision , binary number , similarity (geometry) , noise (video) , inter frame , reference frame , image (mathematics) , telecommunications , mathematics , arithmetic , communication , sociology
Multimedia devices have become increasingly popular due to high quality and low cost products using advanced technology. These devices can capture multimedia files, which can be modified easily by video editing tools. One of the most frequently encountered forgery types in video forensics is the frame duplication (FD) forgery. Many methods have been proposed in the literature to deal with this type of forgery. These methods do not consider frame‐mirroring (FM) attack which copy a sequence of frames and paste its mirrored versions somewhere else on the same video. A new FD/FM detection method is proposed in this work. The method extracts binary features from frames and determines the similarity among features. Peak‐signal‐to‐noise ratio of the candidate frames is used to eliminate some of the large number of candidates to improve the detection of the forged frames. Experimental results show that the proposed method successfully detects FM/FD attacks and also yields better execution time and detection results compared to similar works reported in the literature.