Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Sumitra Dewi
Department Information Technology, STMIK Pelita Nusantara Medan, Indonesia
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
IDENTIFICATION OF BIOMETRIC DEEPFAKES USING FEATURE LEARNING DEEP LEARNING Anita Sindar Sinaga; Arjon Samuel Sitio; Sumitra Dewi
Jurnal Teknik Informatika (Jutif) Vol. 3 No. 4 (2022): JUTIF Volume 3, Number 4, August 2022
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.jutif.2023.4.1.461

Abstract

Improved image quality on several frames extracted from video by manipulating image parameters by improving object edges and coloring segmentation to identify individual human biometric parts. Convolutional Neural Network (CNN) is designed to process two-dimensional data on images by classifying labeled data using the supervised learning method. The classification of fake or not fake images is done using the feature learning Deep Learning technique by forming a Machine Learning model. Video samples (testing and testing) are taken from YouTube randomly. Identifying the resemblance of one person's face to another's (real) face using deep learning. Identifying the resemblance of a person's face to another's face (real) on a genuine or fake label using CNN. Overall, the accuracy results models obtained the highest average accuracy on the face = 93.40%, mouth = 88.52%, eyes = 89.75 %. average accuracy = 90%.
Co-Authors Anita Sindar Sinaga Arjon Samuel Sitio