PFT II Evaluation
These comments provided by Neurotechnology are based on NIST PFT II results published on January 17, 2017.
NIST Proprietary Fingerprint Template Evaluation II (PFT II) is one-to-one verification evaluation which measures the performance of fingerprint matching algorithms by utilizing proprietary fingerprint templates. The samples dataset have been increased to 120,000 subjects compared to previous PFT evaluation. Number of experiments was also increased to 33 with different combinations of single and two fingerprints matching.
In 2017 Neurotechnology fingerprint algorithm was submitted to NIST Proprietary Fingerprint Template Evaluation II. The algorithm 's template matching accuracy was among the best participants in most of the experiments.
Compared to our previous submission 3T, the matching accuracy of the recent submission 3Z (in red) at FMR=0.0001 improved 1.18 times on average. In summary, we present accuracy results as FNMR@FMR=0.0001 for each of 33 experiments:
- 1-9 correspond to plain-to-plain fingerprints matching on AZLA dataset.
- 10-18 correspond to plain-to-rolled fingerprints matching on AZLA dataset.
- 19-27 correspond to rolled-to-rolled fingerprints matching on AZLA dataset.
- 28-30 correspond to plain-to-plain fingerprints matching on DHS2 dataset.
- 31-33 correspond to plain-to-plain fingerprints matching on POEBVA dataset.
Our latest submission 3Z (in red) is among the most accurate algorithms in all experiments.
We also present template extraction and comparison times for seven most accurate recent submissions for all four different dataset:
Our latest submission 3Z (in red) is the fastest during enrollment and second fastest during matching of fingerprint templates. It is also the only one which performs template extraction in under one second in average for any tested dataset – the most common requirement for biometric systems.