Detection of A Facial Forgery Video with MesoNet

Detection of A Facial Forgery Video with MesoNet
Author(s):
Siva Prasad Patnayakuni
Keywords:
Facial forgery, MesoNet, Deepfake, Face2face, Neural Network .
Abstract
This paper gives a technique to routinely and correctly locate face tampering in films, and specifically makes a speciality of current strategies used to generate hyper sensible cast films: Deepfake and Face2Face. Traditional photo forensics strategies are normally now no longer nicely ideal to films because of the compression that strongly degrades the data. Thus, this paper follows a deep getting to know technique and gives networks, each with a low quantity of layers to attention at the mesoscopic residences of images. We examine the ones rapid networks on each present dataset and a dataset we've got constituted from on-line films. The assessments reveal a completely a hit detection fee with extra than 98.4% for Deepfake and 95.3% for Face2Face.
Article Details
Unique Paper ID: 156985 Publication Volume & Issue: Volume 9, Issue 5 Page(s): 570 - 577
Article Preview & Download

Share This Article

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org