AUTOMATIC FACE MASK DETECTION BASED ON MOBILENET V2 AND DENSENET 121 MODELS

Santoso, Albertus Joko and Saragih, Raymond Erz (2022) AUTOMATIC FACE MASK DETECTION BASED ON MOBILENET V2 AND DENSENET 121 MODELS. ICIC Express Letters, 16 (4). pp. 433-440. ISSN 1881-803X

Preview

Text (Albertus Joko Santoso and Raymond Erz Saragih) 12. Automatic Face Mask Detection Based On Mobilnet V2.pdf Download (1MB) | Preview

Abstract

The COVID-19 pandemic has brought significant impacts to the world. In Indonesia, public places such as malls, restaurants, shops, private and government offices, and public areas obliged visitors to wear masks. Unfortunately, there are times when visitors do not obey the rules by not wearing a mask; therefore, surveillance must be conducted. However, manual surveillance to check if a person wearing a mask can be a tedious task. This research aims to propose an automatic face mask detection that can detect if a person is using a mask or not. The proposed method combines face detection and classification using deep learning. The face detection is done using USM sharpening, CenterFace, and two pre-trained models, the MobileNet V2 and DenseNet 121 are used to classify if a person wears a face mask or not. The pre-trained models were fine-tuned using two datasets. Google Colab and libraries such as Tensorflow, Keras, and Scikitlearn were utilized. The research results show that the MobileNet V2 achieves higher performance and has a faster execution time.

Actions (login required)

View Item