University of Notre Dame researchers have developed software that can determine the difference between iris scans using a new method.
Current iris-recognition methods can reach 99.99% accuracy, but these methods are difficult to understand for people without expert knowledge. As a result, identifying people via fingerprints is more common, even through iris recognition is much more accurate, according to Notre Dame graduate student Jianxu Chen.
The researchers wanted to create a new method that is easy to visualize and interpret. "We detect some features on the iris images, so whenever people want to match them, they just find whether you have this feature or that feature," Chen says. "If you see five or six matched features, it's probably a good sign that the irises are from the same person."
Chen notes it is important that people can interpret the results of an iris-recognition test, even if their software is not currently as accurate as more common methods of iris recognition.
Although the new method is only 97 percent to 98 percent accurate, compared to 99.99% with some other methods, the Notre Dame process makes it much easier for people to judge the correctness.
From The Observer (IN)
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found