International Journal of Electrical and Computer Engineering (IJECE) Vol. 12, No. 6, December 2022, pp. 6149~6158 ISSN: 2088-8708, DOI: 10.11591/ijece.v12i6.pp6149-6158  6149 Journal homepage: http://ijece.iaescore.com Social distance and face mask detector system exploiting transfer learning Vijaya Shetty Sadanand, Keerthi Anand, Pooja Suresh, Punnya Kadyada Arun Kumar, Priyanka Mahabaleshwar Department of Computer Science and Engineering, Nitte Meenakshi Institute of Technology, Bengaluru, India Article Info ABSTRACT Article history: Received Aug 16, 2021 Revised Jul 15, 2022 Accepted Aug 9, 2022 As time advances, the use of deep learning-based object detection algorithms has also evolved leading to developments of new human-computer interactions, facilitating an exploration of various domains. Considering the automated process of detection, systems suitable for detecting violations are developed. One such applications is the social distancing and face mask detectors to control air-borne diseases. The objective of this research is to deploy transfer learning on object detection models for spotting violations in face masks and physical distance rules in real-time. The common drawbacks of existing models are low accuracy and inability to detect in real-time. The MobileNetV2 object detection model and YOLOv3 model with Euclidean distance measure have been used for detection of face mask and physical distancing. A proactive transfer learning approach is used to perform the functionality of face mask classification on the patterns obtained from the social distance detector model. On implementing the application on various surveillance footage, it was observed that the system could classify masked and unmasked faces and if social distancing was maintained or not with accuracies 99% and 94% respectively. The models exhibited high accuracy on testing and the system can be infused with the existing internet protocol (IP) cameras or surveillance systems for real-time surveillance of face masks and physical distancing rules effectively. Keywords: Deep learning Face mask classifier MobileNetV2 Social distancing Transfer learning YOLOv3 This is an open access article under the CC BY-SA license. Corresponding Author: Vijaya Shetty Sadanand Department of Computer Science and Engineering, Nitte Meenakshi Institute of Technology Bangalore 560064, Karnataka, India Email: vijayashetty.s@nmit.ac.in 1. INTRODUCTION In recent years, plenty of research has been conducted to develop applications in the realm of computer vision, speech recognition, pattern recognition, and face recognition. Object detection deals with discovering and classifying the objects in an image [1], [2]. Machine learning and deep learning methods have been extensively used in statistical interpretation and extending their applications in computer vision and object recognition. There exist numerous applications of object detection that are evolving lately up such as face mask detection, and pedestrian detection [3]–[5]. Based on the application's point of view, object detection algorithms are ordered as: i) generic object detection and ii) application-oriented detection [6]–[9]. Furthermore, deep learning models are viewed in two forms based on the inferring speed and recognition efficiency: i) one-staged detectors such as the you only look once (YOLO) and ii) two-staged detectors such as the region-based convolutional neural networks (RCNN) [10], [11]. Previously, Jiang’s [5] works suggested a one-staged Retina Face Mask detector to focus on detecting face masks. The paper by Matthias [8], concentrated on real-time face recognition and the intended