Researchers in the United Kingdom have developed a technology that uses shape-finding algorithms to identify people through an unlikely source: their ears.
This is what scientists in the UK are trying to find out. Researchers from the University of Southampton have developed a new algorithm for finding a person’s shape that is 99.6 percent accurate. According to researchers, this new “image-ray-transform” process could be the world’s most accurate and least invasive way to identify people.
Technology advancements
Government agencies have used fingerprints for years to identify individuals. The FBI database in the United States contains 70 million fingerprints from criminals. However, fingerprinting is not an exact science. Fingertips can become damaged by calluses and fingerprints can fade over time.
It is also challenging to scan the eyes with iris scanners, as the eye is a very small target. Fraudulent attempts at scanning the eyes can be made by using a hi-res image, instead of the actual eyeball.
These disadvantages were in mind when scientists from the University of Southampton, UK developed a new technology to allow people to be identified via an area of their body that rarely changes: the ear. “When you are born, your ear is fully formed. Although the lobe may shrink a bit, it remains the same. It’s a great method to identify people,” Mark Nixon (the leader of the research) told Wired Magazine.
How it works
Wired Magazine states that ear identification uses computer visualization to convert human features into IDs. Researchers in Southampton used this technology to create an “image-ray-transform” algorithm that can identify an ear with 99.6 percent accuracy.
The algorithm that produces rays looks for curving features in the ears. Once the rays have located every part of the ears, another program converts these curves into unique numbers. This is called an “ear ID”.
There are ups and downs
There are both positives and pitfalls to using ears to identify individuals. Ear identification systems are limited in the same way as iris scans. They can be blocked by hair, have difficulty lighting, or generate different IDs from different angles. Researchers stress that the ear does not replace biometrics such as fingerprints, but is used to supplement them with another ID system.
Although research into ear identification systems is still in its infancy stages, it is becoming faster and more accurate. It could be used in many scenarios, such as when a security camera captures a profile view showing a suspect in a bank robbery. Nixon stated to Wired Magazine, “We have shown that we can use ears. But can we process data that comes out of a normal situation?” That’s where the real challenge lies.
Recent Comments