DIGITAL METHODS FOR MONITORING HAND HYGIENE AND AUTOMATIC NAIL SEGMENTATION USING COMPUTER VISION TECHNOLOGIES

Abstract

Compliance with hand hygiene is one of the key factors in preventing infectious diseases and ensuring patient
safety in healthcare institutions. In recent years, digital technologies have been increasingly introduced to automate the
monitoring of sanitary and hygienic procedures. This study examines modern computer vision and machine learning
methods for analyzing the condition of hands and determining nail growth parameters.
The aim of this research is to develop a digital approach to monitoring hand hygiene based on the analysis of nail plate
images and the application of segmentation algorithms. As part of the study, a dataset of nail images was created, data
preprocessing was performed, and the effectiveness of several segmentation models, including U-Net, Mask R-CNN,
and YOLOv8-seg, was evaluated.
The results of the study demonstrated that the use of deep learning models provides high segmentation accuracy and
allows automatic detection of nail boundaries and the grown part of the nail. Among the tested models, Mask R-CNN
showed the highest accuracy indicators. The obtained results confirm the potential of artificial intelligence technologies
for digital monitoring of hand hygiene and prevention of infectious disease spread in healthcare institutions