Video Forgery Detection by Bitstream Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Video Forgery Detection by Bitstream Analysis

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Identifiants

  • HAL Id : hal-03776086 , version 1

Citer

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⟩
107 Consultations
82 Téléchargements

Partager

Gmail Facebook X LinkedIn More