Neurotechnology’s palm print matching algorithm tops FVC-onGoing testing
Deep learning-based solutions provider Neurotechnology reported today that the latest FVC-onGoing test results has its palm print recognition algorithm ranked most accurate for both full and partial palm prints, fastest partial palm print matcher and fastest full-print matcher out of the five most accurate matchers. According to the announcement, the Neurotechnology algorithm also has the smallest template size overall, both in full palm print and partial palm print datasets.
“Our expertise in fingerprint recognition technologies carries over to palm print matching,” explains Dr. Justas Kranauskas, head of the biometric research department for Neurotechnology. “Though the palm print is a larger, more detailed recognition task, our experience in this field allows us to bring the most accurate, highest efficiency application available to the palm print recognition market.”
This palm print matching engine is included in Neurotechnology’s MegaMatcher Standard and Extended SDKs. It is suitable for both 1-to-1 and 1-to-many applications.
Last month Neurotechnology released its new server video analytics products with algorithms for facial recognition, vehicle-human classification and tracking, and automatic license plate recognition.