NIST IREX Evaluation Judges VeriEye 2.1 One of the Most Reliable in Iris Recognition
Neurotechnology Also Places in Top Three for Lowest Computational Cost
Vilnius, Lithuania – September 29, 2009 – The National Institute of Standards and Technology (NIST) has judged Neurotechnology (www.neurotechnology.com) as the provider of one of the most reliably accurate iris recognition algorithms in a test of leading providers. The NIST Iris Exchange (IREX) Evaluation judged eighteen state-of-the-art algorithms from ten different providers and found VeriEye 2.1 to be in the top three for accuracy and, of the top three, the fastest matching algorithm by a wide margin. Neurotechnology was the only provider to achieve such high rankings in both areas. IREX testing focused on compressed image recognition and interoperable formats in an attempt to provide data standards to support data exchange, storage and "smart card" use.
"We are pleased with the performance of our VeriEye iris recognition algorithm in IREX 2008," said Justas Kranauskas, VeriEye Project Lead for Neurotechnology. "Our product has been commercially available for just over a year and showed excellent results in these tests. To be ranked by NIST among the most accurate as well as among the lowest in computational cost speaks to the quality of the product and the surety it provides our customers."
Neurotechnology had the fastest overall iris matching algorithm – 25 to 75 times faster than other top ranked competitors – while utilizing an iris template that is 3.5 to 7.5 times smaller than those same competitors' templates.
Top iris recognition algorithms provide reliable identification with a very low false acceptance rate – a major strength in iris biometrics. VeriEye 2.1 was judged among the top performers for iris recognition accuracy in the NIST IREX testing across three large scale iris databases when using either uncompressed raw or cropped/cropped-and-masked/converted-to-concentric-polar and JPEG2000 compressed iris images.
The complete NIST IREX report is available at: iris.nist.gov/irex.
VeriEye 2.1 iris recognition algorithm supports ANSI INCITS 379-2004 (American National Standard for Information Technology - Iris Image Interchange Format) and ISO/IEC 19794-6 (Information technology - Biometric data interchange formats - Iris image data) standards.
The Software Development Kit (SDK) for VeriEye 2.1, as well as other award-winning biometric technologies from Neurotechnology (including MegaMatcher 3.0, VeriFinger 6.1 and VeriLook 3.3) are available with highly competitive licensing options through Neurotechnology or from distributors worldwide. 30-day trial versions with full functionality are also available for download. For more information, go to: www.neurotechnology.com
Neurotechnology is a provider of high-precision biometric fingerprint, face and iris identification algorithms, object recognition technology and software development products. More than 1900 system integrators, security companies and hardware providers integrate Neurotechnology's algorithms and software development technologies into their own products, with millions of customer installations worldwide.
Neurotechnology's identification algorithms have consistently earned the highest honors in some of the industry's most rigorous competitions, including the National Institute of Standards and Technology (NIST)'s Fingerprint Vendor Technology Evaluation (FpVTE) and the Fingerprint Verification Competitions (FVC).
Drawing from years of academic research in the fields of neuroinformatics, image processing and pattern recognition, Neurotechnology was founded in 1990 in Vilnius, Lithuania under the name Neurotechnologija and released its first fingerprint identification system in 1991. Since that time the company has released more than 40 products and version upgrades for identification and verification of objects and personal identity. On April 14, 2008 the company announced an official name change to Neurotechnology.
Jennifer Allen Newton
Bluehouse Consulting Group, Inc.
jennifer (at) bluehousecg (dot) com