Please use this identifier to cite or link to this item:

Impact of Facemasks on Face Detection

File Size Format  
ssym-fall2020-0066.pptx 2.11 MB Microsoft Powerpoint XML View/Open

Item Summary Chapman, Anthony 2021-05-24T17:15:14Z 2021-05-24T17:15:14Z 2020-11
dc.description A student presentation to the Fall 2020 Student Research and Creative Works Symposium
dc.description.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.
dc.format.extent 1 page
dc.language.iso English
dc.publisher University of Hawaiʻi — West Oʻahu
dc.rights Attribution-NonCommercial-NoDerivs 3.0 United States
dc.title Impact of Facemasks on Face Detection
dc.type Presentation
dc.type.dcmi text
Appears in Collections: Fall 2020

Please email if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons