Sistem Otomatis Pendeteksi Wajah Bermasker Menggunakan Deep Learning
Submission Date: 2021-02-27 21:23:50
Accepted Date: 2021-08-31 08:07:15
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 studi 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%
Keywords
Covid-19; computer visions; face detection; deep learning; IoT
CC Licencing
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.
Jurnal Teknik ITS by Direktorat Riset dan Pengabdian Masyarakat (DRPM) ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/teknik.
Statistik Pengunjung