PFT II – Top in accuracy
Innovatrics ranks top in accuracy in NIST PFT II
Innovatrics’ algorithm ranked joint first in accuracy in the recently published Proprietary Fingerprint Template Evaluation II (PFT II), a benchmark test conducted by the US National Institute of Standards and Technology (NIST) to measure the performance of fingerprint matching software.
The 99.98% true match rate, together with the related equal error rates achieved by Innovatrics’ algorithm are the best results ever recorded during PFT evaluations. (TMR@FMR = 0.0001, POEBVA dataset, R/L index).
This unique combination of industry-leading accuracy and top-ranked speed underlines our belief that Innovatrics’ algorithm is the most suitable solution for practical implementation and use with large-scale databases in AFIS solutions.
For inquiries about licensing Innovatrics algorithmLet´s talk
Drop us a line, we will contact you within 24 hours.
About NIST PFT II
The National Institute of Standards and Technology’s Proprietary Fingerprint Template evaluation is an ongoing program to measure the performance of fingerprint matching software by utilizing vendor proprietary fingerprint templates. There have been two phases to the PFT evaluation.
The original PFT evaluation (which is no longer accepting SDKs for evaluation) had only reported the matching algorithm’s accuracy.
The newer PFT II evaluation (which is accepting SDKs for evaluation) also reports matcher accuracy information. In addition PFT II will report template extraction times, template size information and matcher timings. PFT II will use both two finger and ten finger datasets to report results on slap-to-slap, slap-to-roll, and roll-to-roll matching. PFT II continues to be only a 1-to-1 verification evaluation it does not report 1-to-many matching results.
These evaluations are intended to assess the core algorithmic capability of the technology to perform one-to-one verification. These evaluations assesses accuracy of end-stage matchers (i.e. the computationally expensive algorithms used in the very last stages of one-to-many Automated Fingerprint Identification System (AFIS) searches).