Real-Time Visitor Counting with Dynamic Facial Recognition using Python and Machine Learning

Abstract

Visitor data or the number of visitors at a particular location is crucial information to be obtained. This data can serve various purposes, particularly in enhancing customer satisfaction. For instance, predicting the number of visitors at tourist destinations enables tourism management to be better prepared for welcoming and providing optimal services to arriving visitors. Visitor count data can also be employed to automatically restrict visitors during the COVID-19 pandemic, ensuring a safe and comfortable environment with limited attendees. To acquire visitor data, a system capable of accurate visitor detection is required. This research utilizes computer vision to detect visitor faces. The developed system, programmed in Python, functions by detecting visitor faces and conducting a count based on the detected faces. To prevent the same visitor from being detected multiple times, a facial recognition method with dynamic facial data collection is implemented in this study. The constructed system successfully counted 27 out of 28 visitors over a two-day period. However, the system has limitations, particularly in terms of the restricted detection area. Therefore, a physical mechanism mandating visitors to undergo facial scanning and registration needs to be established, ensuring recorded data corresponds to the actual visitor count.