Penerapan Deep Learning Menggunakan Convolutional Neural Network untuk Pengenalan Wajah Ketika Menggunakan Masker

Prasetiyo, Bagus Duwi (2022) Penerapan Deep Learning Menggunakan Convolutional Neural Network untuk Pengenalan Wajah Ketika Menggunakan Masker. Undergraduate thesis, Politeknik Negeri Jember.

[img] Text (Abstract)
E41181215_Bagus Duwi Prasetiyo_Skripsi_Abstract.pdf - Submitted Version
Available under License Creative Commons Attribution Share Alike.

Download (8kB)
[img] Text (Bab 1 Pendahuluan)
E41181215_Bagus Duwi Prasetiyo_Skripsi_Bab 1.pdf - Submitted Version
Available under License Creative Commons Attribution Share Alike.

Download (16kB)
[img] Text (Daftar Pustaka)
E41181215_Bagus Duwi Prasetiyo_Skripsi_Dapus.pdf - Submitted Version
Available under License Creative Commons Attribution Share Alike.

Download (142kB)
[img] Text (Laporan Lengkap)
E41181215_Bagus Duwi Prasetiyo_Skripsi Final.pdf - Submitted Version
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

During the Covid-19 pandemic, the health protocol implemented to prevent transmission of the virus was to wear a mask that covers the nose tightly, but the masks used can complicate the facial recognition system, the facial recognition process fails to recognize faces because the nose and mouth should be clear without obstacles. , covered by a mask. Based on this, the purpose of this study is to apply a Deep Learning work model using the Convolutional Neural Networks method to recognize faces using masks. To test the accuracy of CNN, the CNN model used there are 4 models, 3 models made by yourself, and 1 model using Transfer Learning VGG16, the data used in the study amounted to 30 faces with each face added a digital mask. Augmentation was carried out to increase the data in the training process, then tested on 30 faces using original masks, video testing was also carried out to test the performance of the CNN model in recognizing moving faces. In this study, the test resulted in decreased accuracy between 5 to 30%.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDK
Thesis advisorPuspitasari, Trismayanti DwiNIDN0027029002
Uncontrolled Keywords: Face Recognition, Mask, Face Mask Recognition, Deep Learning, Convolutional Neural Network
Subjects: 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika
Divisions: Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika (Bondowoso) > Tugas Akhir
Depositing User: Bagus Duwi Prasetiyo
Date Deposited: 29 Jun 2022 08:17
Last Modified: 29 Jun 2022 08:17
URI: https://sipora.polije.ac.id/id/eprint/12930

Actions (login required)

View Item View Item