How super-recognizers see what the rest of us are missing

SSome people never forget a face. A brief encounter at a party may be enough for them to imprint that person’s face so indelibly on their minds that they will recognize them years later, even enough to spot them among a sea of ​​faces on a city street. People with this strange ability are known as super-recognizers. They make up 1 to 2 percent of the population and their talents are thought to be genetically inherited rather than acquired.

It’s a sought-after skill. Super-recognizers are better than AI at many facial recognition tasks, and people who score well on facial recognition tests can earn a professional license as a super-recognizer, allowing them to work with law enforcement.

Recently, scientists have figured out how to do this: It’s less about how much information about a face they can absorb and process in their brains and more about the quality of the information they absorb. The researchers published their results in the journal Proceedings of the Royal Society B: Biological Sciences.

“Super-recognizers don’t just look tougher, they look smarter. They choose the most useful parts of a face to consider,” James Dunn, a researcher at the School of Psychology at the University of New South Wales in Sydney and lead author of the research, said in a statement. “Our previous research shows that super-recognizers make more fixations and explore faces more widely. Even when we take into account that they looked at more parts of the face, it turns out that what they look at is also more valuable for identifying people.”

Read more: »Human super-recognizers see faces better than AI»

The researchers used eye tracking on 37 super-recognizers, mapping where and for how long they looked at photos of faces on a computer screen. They did the same for 68 people with average facial recognition skills. They then fed the information collected from the different groups of participants to nine different neural networks, trained to recognize faces, and asked the AI ​​networks to decide whether two faces belonged to the same person.

“AI has become very good at facial recognition,” Dunn said. “Our goal was to exploit this to understand which models of the human eye were most informative.”

The AI ​​was much better at matching faces when fed the eye tracking models of super recognizers than those of average recognizers. This was true even when the total amount of visual information was the same and even when the face was partially hidden.

One reason super-recognition can be difficult to learn is that although some features are on average more critical for recognition, such as eyes, evidence suggests that the features most useful for recognizing and identifying a particular face will differ from person to person. This may be why super-recognizers focus their gaze on the face rather than on critical individual features.

The findings upend previous assumptions about why super-recognizers are so good at recognizing faces: it comes down to differences in how they encode information on the retina rather than how they process visual information after it reaches the brain.

The researchers note that their study focused on facial recognition in still images, while future studies could examine how super-recognizers are able to identify faces in a changing context such as video.

Either way, it seems you can’t hide from a super-recognizer.

Are you a super-recognizer? Take one of these tests:

The UNSW (University of New South Wales) facial test

The Cambridge Facial Memory Test (Birbeck University of London)

Enjoy Nautilus? Subscribe to our free newsletter.

Main image: Fractal Images / Shutterstock

• Kristen French

  Published on November 5, 2025

  Kristen French is an associate editor at Nautilus. She has worked in science journalism since 2013, reporting and writing articles and news for publications such as Wired, Backchannel, The Verge, And New York Review. She holds a master’s degree in science journalism from Columbia University.