Deep Learning for Forgery Face Detection Using Fuzzy Fisher Capsule Dual Graph

Abstract

In digital manipulation, creating fake images/videos or swapping face images/videos with another person is done by using a deep learning algorithm is termed deep fake. Fake pornography is a harmful one because of the inclusion of fake content in the hoaxes, fake news, and fraud things in the financial. The Deep Learning technique is an effective tool in the detection of deep fake images or videos. With the advancement of Generative adversarial networks (GAN) in the deep learning techniques, deep fake has become an essential one in the social media platform. This may threaten the public, therefore detection of deep fake images/videos is needed. For detecting the forged images/videos, many research works have been done and those methods are inefficient in the detection of new threats or newly created forgery images or videos, and also consumption time is high. Therefore, this paper focused on the detection of different types of fake images or videos using Fuzzy Fisher face with Capsule dual graph (FFF-CDG). The data set used in this work is FFHQ, 100K-Faces DFFD, VGG-Face2, and Wild Deep fake. The accuracy for FFHQ datasets, the existing and proposed systems obtained the accuracy of 81.5%, 89.32%, 91.35%, and 95.82% respectively.

Image Content Forgery Detection Model Combining PSO and SVM in Electronic Data Forensics

“…This improvement was significant compared to similar models in other literature. For instance, Arunkumar P M's research team's fuzzy Fisher face model detection method achieved an accuracy of 89.32% in the dataset [12]. Styawati S's research team achieved the highest accuracy of 89% in sentiment classification using an SVM-based model [13].…”

“…To design an effective method that can accurately detect in-depth forged images or videos, the research team of Arunkumar P M proposed to utilize deep learning techniques and introduced a fuzzy Fisher face model with capsule biplots to detect different types of fake images or videos. The results showed that the method achieved 89.32% accuracy in the dataset [12].…”

“…In equation ( 11),  and  denote the relaxation variable outside the hyperplane and the relaxation variable inside the hyperplane, respectively. The mathematical expression of the linear SVM regression function is shown in equation (12).…”

Improving Accuracy of Face Recognition in the Era of Mask-Wearing: An Evaluation of a Pareto-Optimized FaceNet Model with Data Preprocessing Techniques

“…The study considered only the faces of healthy people; however, it is known that some diseases such as facial palsy can significantly distort the characteristics of the face [95] while distorting its symmetry features [96], which can negatively affect biometric recognition using face. Additionally, the study did not consider adversarial attacks or attempts at face forgery with the aim of concealing identity or performing impersonation, which can decrease the performance of face recognition [97], Finally, the study did not address the fact that the use of masks to conceal faces may be done for legitimate reasons and not only by criminals. Therefore, the study did not consider the impact of increasing facial recognition accuracy in individuals who wear masks for safety or medical reasons.…”