Ears could be an effective alternative to fingerprints and facial recognition, new research shows. Each is as unique as fingerprints and changes less over time than a face.
A research team at the University of Georgia has developed an ear recognition system that is up to 99% accurate and could be a reliable alternative for technology requiring face or fingerprint recognition.
Just like fingerprints, ears are unique to every individual – even identical twins have different ones, researchers say. Unlike the face, ears remain relatively unchanged over the years, except for the earlobe dropping lower as time passes.
The technology works much the same way fingerprint or face recognition does, according to researchers. It scans your ears and draws a biometric picture of them, logging multiple samples into the device. You can then unlock the device if your ears match the logs.
“The phone captures multiple samples of a person’s identity, and the images are temporarily saved in your device,” Thirimachos Bourlai, lead author of the study, said in a university statement.
“Just like you have to use a live fingerprint to unlock your phone and compare it to your registered one, you would have to use the live ear to unlock it,” he said.
The untapped potential of ear recognition did not go unnoticed by technology companies. Apple filed a patent with the US Patent and Trademark Office earlier this year that suggests AirPods could be used to identify a person by the shape of their ear canal – and prevent their use by an unauthorized party.
In 2015, Amazon patented its own ear recognition technology that identifies a person based on the share of their ear.
“There are many unique ways to recognize individuals utilizing other traditional modalities, such as through their face, fingerprints, and iris. Ear recognition is just another exciting modality that we need to start talking more about due to its benefits, despite the understandable challenges of self-capturing an ear image,” Bourlai said.
The University of Georgia’s research team sees its technology applied in situations where facial recognition is not possible, for example, when someone is wearing a mask. It could also be used to enhance existing security systems in places like airports, as well as camera-based security systems, the researchers said.
Further research will focus on making the ear recognition algorithm work with thermal images and in darker environments, where conventional cameras may struggle to capture a clear picture.
The study was published in an IEEE Access peer-reviewed journal.
More from Cybernews:
Subscribe to our newsletter