当前位置: X-MOL 学术Appl. Nanosci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deepfake detection using rationale-augmented convolutional neural network
Applied Nanoscience Pub Date : 2021-09-13 , DOI: 10.1007/s13204-021-02072-3
Saadaldeen Rashid Ahmed Ahmed 1 , Emrullah Sonuç 1
Affiliation  

Deepfake network is a prominent topic of research as an application to various systems about security measures. Although there have been many recent advancements in facial reconstruction, the greatest challenge to overcome has been the means of finding an efficient and quick way to compute facial similarities or matches. This work is created utilizing the rationale-augmented convolutional neural network (CNN) on MATLAB R2019a platform using the Kaggle DeepFake Video dataset with an accuracy of 95.77%. Hence, real-time deepfake facial reconstruction for security purposes is difficult to complete concerning limited hardware and efficiency. This research paper looks into rational augmented CNN state-of-the-art technology utilized for deepfake facial reconstruction via hardware such as webcams and security cameras in real time. Additionally, discuss a history of face reconstruction and provide an overview of how it is accomplished.



中文翻译:

使用基本原理增强的卷积神经网络进行 Deepfake 检测

Deepfake 网络是一个突出的研究课题,作为对各种安全措施系统的应用。尽管最近在面部重建方面取得了许多进展,但要克服的最大挑战是找到一种有效且快速的方法来计算面部相似性或匹配性。这项工作是在 MATLAB R2019a 平台上利用基本原理增强卷积神经网络 (CNN) 创建的,使用 Kaggle DeepFake 视频数据集,准确率为 95.77%。因此,由于硬件和效率有限,难以完成用于安全目的的实时深度伪造面部重建。这篇研究论文探讨了通过网络摄像头和安全摄像头等硬件实时进行深度伪造面部重建的合理增强 CNN 最先进技术。此外,

更新日期:2021-09-14
down
wechat
bug