SEPTIYANTO, RIFKI AGUS (2025) FACE MASK DETECTION SYSTEM USING SINGLE SHOT MULTIBOX DETECTOR AND MOBILENETV2 ALGORITHMS. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5180411175_RIFKI AGUS SEPTIYANTO_ABSTRAK.pdf Download (126kB) |
Abstract
The COVID-19 pandemic has necessitated strict adherence to face mask usage as part of public health protocols, yet manual monitoring remains inefficient and prone to human error. This study aims to develop a real-time face mask detection system based on deep learning, employing a combination of the Single Shot Multibox Detector (SSD) algorithm and the MobileNetV2 architecture to achieve high accuracy with low computational cost. The dataset comprises 139 facial images divided into three classes: correctly wearing a mask (50 images), not wearing a mask (49 images), and improperly wearing a mask (40 images). The data underwent augmentation techniques (horizontal flip, rotation between -15° and +15°, brightness adjustment between -20% and +20%, and noise addition up to 1.09 pixels) and preprocessing (resizing to 640x640 pixels and grayscale conversion). The SSD model was constructed with MobileNetV2 as the backbone and trained using the Adam optimizer (learning rate 0.001) along with a loss function. Testing results showed the system achieved an accuracy of 64% and an inference speed of 4 FPS at an IoU threshold of 0.5, meeting the criteria for real-time detection while maintaining acceptable accuracy. The findings confirm that integrating SSD with MobileNetV2 is an effective solution for automatic, accurate, and efficient face mask detection, with promising applications in public surveillance systems utilizing edge computing. Keywords: Face Mask Detection, SSD, MobileNetV2, Deep Learning, Real-Time System.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 25 Jul 2025 03:40 |
| Last Modified: | 25 Jul 2025 03:40 |
| URI: | http://eprints.uty.ac.id/id/eprint/18370 |
Actions (login required)
 |
View Item |
