While face masks and coverings have kept many of us safe during the covid-19 pandemic, they have also affected a key daily activity that is essential to everyone: recognizing a person’s face.
In a recently published study in the journal Scientific Reports, researchers from York University, Canada and Ben-Gurion University of the Negev (BGU) in Israel, revealed how identifying people wearing masks has presented a unique challenge during the ongoing pandemic.
For this experiment, researchers Tzvi Ganel, a professor and head of the Laboratory for Visual Perception and Action at the BGU Department of Psychology, and Erez Freud, a faculty member at York University, used a modified version of the Cambridge Face Memory Test. This is a standard test for assessing facial perception among people, and this particular version included both masked and unmasked faces. The study was conducted online with a group of nearly 500 people.
The findings revealed that the success rate of identifying someone wearing a mask was reduced by 15%. “This could lead to many errors in correctly recognizing people we know," says professor Galia Avidan, who is a member of the BGU Department of Psychology and the Department of Cognitive and Brain Sciences, and an expert on facial recognition and perception. “Face masks could be even more challenging to people whose face recognition skills are not ideal to begin with and cause greater impairment,” Avidan says in an official release.
The research team also found that masks specifically interfered with extracting a “holistic impression of faces” and led to feature-by-feature processing which is a less accurate and more time-consuming strategy. In simple terms, Instead of looking at the entire face, people are now looking at eyes, nose, cheeks, and other visible elements separately to construct an entire facial face percept - something we used to do instantly, the researchers say.
“Faces are among the most informative and significant visual stimuli in human perception and play a unique role in communicative, social daily interactions,” the researchers explain in an official release, adding that the unprecedented effort, in the form of face masks, to minimize covid-19 transmission had created a new dimension in facial recognition. The researchers say future work in this area should focus on the social and psychological implications of wearing masks on human behavior.
While the sample size for this research is definitely small compared to the mammoth number of users who wear a face mask around the world, it is a real-life problem that has left a slew of smartphone makers in a fix. Earlier this year, multiple news reports noted how face masks were becoming a problem for facial recognition software and algorithms in smartphones. Apple’s Face ID system was a case in point. Several iPhone users around the world complained that the system would not work when they tried unlocking their phone with a face mask on. Apart from adding an option to use a passcode as an alternative, Apple is reportedly considering bringing back its Touch ID system, which uses a person's fingerprint to unlock a device.