Human face recognition of unfamiliar faces : the effects of disguises and lighting

Disguises such as masks have steadily been on the rise, as measures are taken to combat the COVID-19 pandemic. As such, disguises have become an important part of our daily lives, affecting social interactions and face recognition. This study investigated the effects of disguises and lighting on fac...

Full description

Saved in:
Bibliographic Details
Main Author: Ng, Kester Yi Jie
Other Authors: Charles Or
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/148331
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Disguises such as masks have steadily been on the rise, as measures are taken to combat the COVID-19 pandemic. As such, disguises have become an important part of our daily lives, affecting social interactions and face recognition. This study investigated the effects of disguises and lighting on face recognition, using a face memory task of the ‘old’/’new’ paradigm. Participants were required to memorise face images (‘old’) and identify the faces that were familiar to them among a series of ‘old’ and ‘new’ faces after the memory stage. Disguises were superimposed onto the faces, creating three conditions: Full face (no disguise), Mask and Sunglasses conditions. All participants completed the three conditions. Additionally, half of the participants completed the study with faces brightly lit, while the other half viewed face images dimly lit. The study found that face recognition was most affected in the Sunglasses condition, while the Full face condition elicited the highest accuracy. One surprising finding was face recognition performance was higher on average in the Dim conditions as compared to the Bright conditions. Our findings demonstrate the relative impact of disguises on face recognition abilities, which have important implications on areas such as security and personal verification.