作者: Amir Bidokhti , Shahrokh Ghaemmaghami
DOI: 10.1109/AISP.2015.7123529
关键词:
摘要: With rapid proliferation of affordable video capturing devices and state-of-the-art editing software tools, it is now easier than ever to manipulate contents. In this paper a passive method for copy/move forgery detection in MPEG videos proposed. The first divides each frame into suspicious apparently innocent parts. Subsequently, an optical flow coefficient computed from part. Forgeries are located when unusual trend the object detected. Experiments on set forged original sequences validate justifications made by proposed method.