Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Pixel : Jurnal Ilmiah Komputer Grafis
Ibnu Halim Mustofa
Universitas Stikubank Semarang
Education

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

Found 1 Documents
Search

 1 
Sistem Pengenalan Wajah Bermasker dengan Metode Convolutional Neural Network Ibnu Halim Mustofa; Edy Winarno
Pixel :Jurnal Ilmiah Komputer Grafis Vol 16 No 1 (2023): Vol 16 No 1 (2023): Jurnal Ilmiah Komputer Grafis
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/pixel.v16i1.1062

Abstract

Face is one of the unique parts of the human body and can be used for identification purposes. Research on the application of facial recognition biometric technology has been carried out since 1960 and continues to be refined to this day. Humans can easily recognize an object or image, but not for a computer. This is the background behind the creation of a scientific discipline called Computer Vision. One deep learning algorithm that has been extensively researched and used for classifying various images is Convolutional Neural Network (CNN). The COVID-19 requires us to comply with health protocols, one of which is by wearing a mask when doing activities outside the home. The biometric presence system that is commonly used today can pose a risk of transmission because they have to touch the surface of an object that may have been contaminated from someone infected with the COVID-19 virus. Seeing the risks posed and the relevance to the times when people are accustomed to wearing masks, a study was conducted to create a masked face recognition system using the Convolutional Neural Network (CNN) method with VGG16 architecture. The dataset used was in the form of people's faces who were willing to be the object of research. This study produced highest accuracy rate of 85,71% with the application of various types of masks, namely surgical, cloth, and KF94 masks.
Co-Authors Edy Winarno