Video Forgery Detection by Bitstream Analysis - Archive ouverte HAL Access content directly
Conference Papers Year :

Video Forgery Detection by Bitstream Analysis

Abstract

In this paper, we propose a video tampering detection method based on bitstream analysis for videos in H.264 or MPEG-4 AVC format. This method aims at detecting inter-frame alterations: insertion, deletion, permutation, duplication. Features are extracted from the original bitstream. This method therefore does not require the decoding of the video, which improves the speed of analysis. The detection quality remains very significant in terms of binary detection, tampered / pristine video, with a F1 measure equal to 94.89. Concerning multiclass classification, F1 measure reaches 70.33 due to the difficulty to separate swap and duplication forgeries.
Fichier principal
Vignette du fichier
CVCS2022.pdf (837 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03776086 , version 1 (13-09-2022)

Identifiers

  • HAL Id : hal-03776086 , version 1

Cite

Hugo Jean, Emmanuel Giguet, Christophe Charrier. Video Forgery Detection by Bitstream Analysis. Colour and Visual Computing Symposium 2022 (CVCS 2022), Sep 2022, Gjøvik, Norway. ⟨hal-03776086⟩
83 View
45 Download

Share

Gmail Facebook Twitter LinkedIn More