We're used to thinking about eyes and fingerprints getting scanned when a character in a movie goes into a high-tech facility. Well, what if they had their ears scanned, too? Turns out it's a pretty accurate way to tell people apart — like 99.6% accurate.
The research, being done at the University of Southampton in the U.K., involves a technique called image ray transforming that can pick out the tubular structure of the ear, isolate it from the rest of the head, and then pick out unique characteristics about it.
Of course, ears can be obstructed in all kinds of ways — the most common being by our hair. The team came up with an algorithm to deal with the likes of hair or the irregularities caused by wearing a pair of glasses, and in a test using 252 images enjoyed a 99.6% success rate.
According to Science 2.0, this isn't the first time ears have been used for biometric identification, and in fact there's a benefit to using them:
Professor Mark Nixon, one of the UK's earliest researchers in this field, first used ears as a viable biometric back in 1999. Back then, he said that ears have certain advantages over more established biometrics as they have a rich and stable structure that is preserved from birth to old age and instead of aging they just get bigger. The ear also does not suffer from changes in facial expression and it is firmly fixed in the middle of the side of the head against a predictable background, unlike face recognition which usually requires the face to be captured against a controlled background.
In fact, ears may not be the only tubular structure the image ray transform technique can handle, according to Alastair Cummings, a PhD student working on the project. "Feature recognition is one of the biggest challenges of computer vision," he said. "The ray transform technique may also be appropriate for use in gait biometrics, as legs act as tubular features that the transform is adept at extracting."
At some point a scanner will be able to know who you are in the blink of an eye just by looking at any part of you. Pretty scary, no?