Pengembangan aplikasi deteksi masker wajah pada area wajib masker

Wiputra, Timothy (2022) Pengembangan aplikasi deteksi masker wajah pada area wajib masker. Bachelor thesis, Universitas Pelita Harapan.

[img]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (219kB) | Preview
[img]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (321kB) | Preview
[img]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (304kB) | Preview
[img]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (305kB) | Preview
[img] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[img] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (757kB)
[img] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[img] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (296kB)
[img]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (261kB) | Preview
[img] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (512kB)

Abstract

At the time this research was written, the whole world was experiencing Covid-19. The spread of Covid-19 is so fast that it requires the public to implement health protocols. However, in practice, there are still many people who do not wear masks, especially in public spaces which increases the risk of spreading Covid-19. Therefore, it is necessary to build an application for detecting the use of face masks in the mandatory mask area in real time. This study implements the Deep Neural Network algorithm, specifically Convolutional Neural Network (CNN) using the Tensorflow and Keras libraries to distinguish human faces who wear and do not wear masks. The total available dataset is 9792 which is divided into 2, image wearing mask (4883 data) and image not wearing mask (4909 data). The experiment is carried out in several scenarios, starting from 1 to 4 people, facing various directions and distance from camera to the subject ranging from 0.5 to 4 meters. Based on the results of the research, the mask detection application was tested in several scenarios and obtained an average accuracy value of 87.86%, which means that the application built is quite accurate in detecting the use of human face masks./ Pada saat penelitian ini ditulis, seluruh dunia sedang mengalami sebuah pandemi yaitu Covid-19. Penyebaran Covid-19 dari orang yang terinfeksi virus ke orang lain sangat cepat sehingga membutuhkan masyarakat untuk menerapkan protokol kesehatan terutama dengan selalu memakai masker. Namun pada praktiknya, masih banyak masyarakat yang tidak menggunakan masker terutama ketika berada di ruang publik yang dapat meningkatkan resiko penyebaran Covid-19. Oleh sebab itu, maka perlu dibangun sebuah aplikasi deteksi pemakaian masker wajah pada area wajib masker secara real time. Penelitian ini mengimplementasikan algoritme Deep Neural Network, lebih spesifiknya Convolutional Neural Network (CNN) pada library Tensorflow dan Keras untuk membedakan wajah manusia yang menggunakan masker dan tidak menggunakan masker. Dataset yang tersedia adalah sebanyak 9792 data yang dibagi menjadi 2 yaitu citra memakai masker sebanyak 4883 data dan citra tidak memakai masker sebanyak 4909 data. Pengujian aplikasi ini dilakukan dengan beberapa skenario yaitu dimulai dari 1 hingga 4 orang, wajah menghadap ke berbagai arah dan jarak kamera dengan subjek mulai dari 0,5 meter hingga 4 meter. Berdasarkan hasil penelitian yang dilakukan, pengujian aplikasi deteksi masker ini dilakukan dalam beberapa skenario dan mendapatkan nilai rata-rata akurasi sebesar 87,86%, artinya aplikasi yang dibangun cukup akurat dalam mendeteksi pemakaian masker wajah manusia.

Item Type: Thesis (Bachelor)
Creators:
CreatorsNIMEmail
Wiputra, TimothyNIM03082180059timothy_wiputra@hotmail.com
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorRobin, RobinNIDN0116128001robin80huang@gmail.com
Uncontrolled Keywords: face mask detection; computer vision; keras; tensorflow
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Depositing User: Users 24143 not found.
Date Deposited: 19 Aug 2022 05:57
Last Modified: 19 Aug 2022 05:57
URI: http://repository.uph.edu/id/eprint/49814

Actions (login required)

View Item View Item