Hand Hygiene Video Classification Based on Deep Learning

TL;DR

This paper reviews gesture recognition literature and implements a deep learning-based system to classify hand hygiene gestures, achieving over 60% accuracy on a subset of handwashing movements.

Contribution

It introduces a simple classification system for hand hygiene gestures using pretrained ResNet-50 and provides a dataset for future expansion.

Findings

Achieved >60% accuracy on classifying handwashing gestures

Utilized pretrained ResNet-50 for gesture classification

Identified the need for larger datasets and more classes in future work

Abstract

In this work, an extensive review of literature in the field of gesture recognition carried out along with the implementation of a simple classification system for hand hygiene stages based on deep learning solutions. A subset of robust dataset that consist of handwashing gestures with two hands as well as one-hand gestures such as linear hand movement utilized. A pretrained neural network model, RES Net 50, with image net weights used for the classification of 3 categories: Linear hand movement, rub hands palm to palm and rub hands with fingers interlaced movement. Correct predictions made for the first two classes with > 60% accuracy. A complete dataset along with increased number of classes and training steps will be explored as a future work.