Innovatrics fingerprint algorithm sets record for 1B matches per second

August 11, 2017 - 

Innovatrics’ latest version of its fingerprint matching algorithm has set a new matching speed record of 1.04 billion matches per second, on a single server only.

The move comes just over a month after Innovatrics launched the new version of Latent Editor, which simplifies the editing and enhancement of latent fingerprint images to increase the probability of a match in an AFIS (Automatic Fingerprint Identification System).

The algorithm outperformed the previous record of 720 million matches per second, which was also held by Innovatrics.

The testing was conducted using the Intel Xeon Platinum 8180 processor on Intel’s latest Skylake architecture.

“We are very pleased to be the first biometrics company to achieve more than 1 billion matches per second with our fingerprint algorithm,” Jan Lunter, Innovatrics founder and CTO, said. “Well-deserved credit goes to our R&D team who has put a lot of work into ensuring that the Innovatrics algorithm remains the fastest, most accurate, and most interoperable on the market. Furthermore, this significant improvement in performance levels will result in even more cost savings for our large AFIS customers.”

Innovatrics said real success is in its ability to increase the algorithm’s matching speed by over 40 percent while “maintaining an industry-leading accuracy”.

As a result, Innovatrics has further improved the operational ranking of its algorithm.

“This landmark achievement is the latest in a long series of Innovatrics technological breakthroughs, underlining our commitment to continuous improvement and innovation for identity management projects,” Lunter said.

Leave a Comment

comments

About Justin Lee

Justin Lee has been a contributor with Biometric Update since 2014. Previously, he was a staff writer for web hosting magazine and website, theWHIR. For more than a decade, Justin has written for various publications on issues relating to technology, arts and culture, and entertainment. Follow him on Twitter @BiometricJustin.