Impact of Facemasks on Face Detection

Date
2020-11
Authors
Chapman, Anthony
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
University of Hawaiʻi — West Oʻahu
Volume
Number/Issue
Starting Page
Ending Page
Alternative Title
Abstract
Research suggests that COVID-19 facemasks degrade the performance of face detection technology. The purpose of this study is to quantify this effect and identify the ideal way to train face detection models when facemasks are present. To do this, I trained a machine learning model for face detection with 1,000 regular human faces using the You Only Look Once (YOLOv4) object detection framework. I tested the face detection capabilities of the model on both regular human faces and masked faces, recording the accuracy and recall rate for each group. I then trained a new model, incorporating masked faces into the initial training dataset. The adjusted model was tested to determine if the adjusted training set imporoved performance. This research will benefit machine learning researchers and data scientists who will train and utilize facial recognition models in the midst of COVID-19 and beyond.
Description
A student presentation to the Fall 2020 Student Research and Creative Works Symposium
Keywords
Citation
Extent
1 page
Format
Geographic Location
Time Period
Related To
Table of Contents
Rights
Attribution-NonCommercial-NoDerivs 3.0 United States
Rights Holder
Local Contexts
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.