Sistem Otomatis Pendeteksi Wajah Bermasker Menggunakan Deep Learning

Baay, Mufid Naufal (2021) Sistem Otomatis Pendeteksi Wajah Bermasker Menggunakan Deep Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 07111640000158-Undergraduate_Thesis.pdf]
Preview
Text
07111640000158-Undergraduate_Thesis.pdf

Download (3MB) | Preview

Abstract

COVID-19 merupakan virus yang telah dinyatakan sebagai pandemi oleh WHO, dan di indonesia sendiri menetapkan COVID-19 sebagai bencana nasional melalui Keputusan Presiden Nomor 12 Tahun 2020. Sumber utama transmisi dari virus ini berasal dari percikan pernapasan atau droplet yang salah satu pencegahan penyebarannya adalah dengan penggunaan masker. Saat ini, pemerintah sedang memberlakukan new normal. Walaupun beraktivitas di lingkungan luar, protokol kesehatan wajib diikuti dan seluruh masyarakat harus disiplin dalam menjalaninya. Pada tugas akhir ini dirancang sebuah sistem otomatis pendeteksi wajah bermasker menggunakan deep learning dalam menjalankan fungsinya. Sistem yang dirancang menggabungkan model deep learning, detektor wajah, dan program tracking dan counting menjadi sebuah sebuah sistem otomatis yang dibantu oleh Graphic User Interface (GUI) serta sebuah perangkat alarm dan platform Internet of Things dalam pemakaiannya. Berdasarkan hasil pengujian yang dilakukan mengikuti batasan masalah yang telah dirumuskan, model memiliki tingkat akurasi klasifikasi pada dataset test sebesar 99%. Implementasi pada Raspberry Pi 4 menunjukkan sistem berbasis model deep learning yang telah dibuat sukses melakukan deteksi, tracking dan counting yang datanya dikirimkan kepada alarm yang dirancang dan sebuah platform IoT, Ubidots. Performa deteksi maksimal dicapai saat objek deteksi bergerak 0,7 m/s, pencahayaan ≥ 100 lux, dan penggunaan modul TensorFlow Lite pada sistem dengan akurasi sebesar 85,7%. Hasil perbandingan dengan metode deteksi lain menunjukkan karakterisasi model deep learning memiliki akurasi deteksi sebesar 82%, lebih tinggi dari metode Haar classifier dengan akurasi 53% walaupun waktu proses yang dilakukan lebih lama 23% dalam menjalankan fungsi sistem.
================================================================================================
COVID-19 is a virus that has been declared a pandemic by WHO, and in Indonesia itself has designated COVID-19 as a national disaster through Presidential Decree No.12 of 2020. The main source of transmission of this virus comes from respiratory droplets, one of which is to prevent its spread. with the use of a mask. Currently, the government is implementing a new normal. Despite activities in the outside environment, health protocols must be followed and the whole community must be disciplined in carrying them out. In this final project, an automatic masked face detection system using deep learning is designed to carry out its function. The system designed to combine deep learning models, face detectors, and tracking and counting programs into an automatic system that is assisted by a Graphic User Interface (GUI) as well as an alarm device and the Internet of Things platform in its use. Based on the results of the tests carried out following the defined problem boundaries, the model has a classification accuracy rate on the test dataset of 99%. The implementation on the Raspberry Pi 4 shows that the deep learning model-based system that has been made successfully performs detection, tracking and counting whose data is sent to the designed alarm and an IoT platform, Ubidots. Maximum detection performance is achieved when the detection object moves 0.7 m / s, object illumination ≥ 100 lux, and the use of the TensorFlow Lite module on the system with an accuracy of 85.7%. Comparison results with other detection methods show deep learning model characterization has a detection accuracy of 82%, higher than the Haar classifier method with an accuracy of 53% even though the processing time is 23% longer in carrying out system functions.

Item Type: Thesis (Other)
Uncontrolled Keywords: Covid-19, Computer Vision, Face Detection, Deep Learning, IoT
Subjects: Q Science > QA Mathematics > QA76 Computer software
Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms
Depositing User: Mufid Naufal Baay
Date Deposited: 26 Feb 2021 00:58
Last Modified: 05 Jul 2024 15:14
URI: http://repository.its.ac.id/id/eprint/82859

Actions (login required)

View Item View Item