Deep Fake Image Classification Using VGG-19 Model

Fake images, also known as "deepfakes," are a growing concern in today's digital age. These images are often created with the intent of benefiting one party and can be difficult to distinguish from real images. They are often disseminated through digital media and newspapers, and can...

Full description

Saved in:
Bibliographic Details
Published in:Ingénierie des systèmes d'Information 2023-04, Vol.28 (2), p.509-515
Main Authors: Killi, Chandra Bhushana Rao, Balakrishnan, Narayanan, Rao, Chinta Someswara
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Classification
Datasets
Deception
Deep learning
Digital imaging
False information
Image classification
Image manipulation
Literature reviews
Methods
Neural networks
Social networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fake images, also known as "deepfakes," are a growing concern in today's digital age. These images are often created with the intent of benefiting one party and can be difficult to distinguish from real images. They are often disseminated through digital media and newspapers, and can spread misinformation or propaganda, which can have serious consequences if not detected and addressed. To effectively detect image falsification in many image data, an architectural model that can process several pixels in the image is required, as well as a method that is effective and adjustable with training data for practical use in daily life. In this paper to detecting fake images usingVGG19 is a convolutional neural network (CNN) architecture that has been successful in a variety of image classification tasks. The proposed VGG19 is better model compared existing models it provides 96% accuracy.
ISSN:1633-1311
2116-7125
DOI:10.18280/isi.280228