VeriFinger SDK

Fingerprint identification for stand-alone or Web solutions

VeriFinger is a fingerprint identification technology designed for biometric systems developers and integrators. The technology assures system performance with fast, reliable fingerprint matching in 1-to-1 and 1-to-many modes.

Available as a software development kit that allows development of stand-alone and Web-based solutions on Microsoft Windows, Linux, Mac OS X, iOS and Android platforms.

Reliability Tests

We present the testing results to show VeriFinger 9.0 template matching algorithm reliability on the data from different fingerprint readers.

Flat fingerprint image datasets used for VeriFinger 9.0 algorithm testing
  Experiment 1 Experiment 2 Experiment 3
Fingerprint reader model DigitalPersona
U.are.U 5100
Futronic FS80 Cross Match
Verifier 300 LC 2.0
Image count 11900 8600 10400
Subject count 73 43 67
Unique finger count 730 430 670
Session count 10 - 20 20 10 - 20
Image size (pixels) 252 x 324 320 x 480 640 x 480

Two tests were performed during each experiment:

  • Test 1 maximized matching accuracy. VeriFinger 9.0 algorithm reliability in this test is shown as blue curves on the ROC charts.
  • Test 2 maximized matching speed. VeriFinger 9.0 algorithm reliability in this test is shown as red curves on the ROC charts.

Receiver operation characteristic (ROC) curves are usually used to demonstrate the recognition quality of an algorithm. ROC curves show the dependence of false rejection rate (FRR) on the false acceptance rate (FAR).

Experiment 1
VeriFinger 9.0 ROC chart calculated using Neurotechnology internal fingerprint DB collected with DigitalPersona U.are.U 5100 scanner
Click to zoom
Experiment 2
VeriFinger 9.0 ROC chart calculated using Neurotechnology internal fingerprint DB collected with Futronic FS80 scanner
Click to zoom
Experiment 3
VeriFinger 9.0 ROC chart calculated using Cross Match Verifier 300 LC 2.0 scanner
Click to zoom
Experiment 1
VeriFinger 9.0 ROC chart calculated using Neurotechnology internal fingerprint DB collected with DigitalPersona U.are.U 5100 scanner
Experiment 2
VeriFinger 9.0 ROC chart calculated using Neurotechnology internal fingerprint DB collected with Futronic FS80 scanner
Experiment 3
VeriFinger 9.0 ROC chart calculated using Neurotechnology internal fingerprint DB collected with Cross Match Verifier 300 LC 2.0 scanner
VeriFinger 9.0 algorithm reliability tests
  Experiment 1 Experiment 2 Experiment 3
Test 1 Test 2 Test 1 Test 2 Test 1 Test 2
Average tempate size (bytes) 3230586 5584974 5245910
FRR at 0.01 % FAR 1.6570 %2.5120 % 0.6940 %0.9755 % 0.4839 %0.9493 %
FRR at 0.001 % FAR 2.0760 %3.3280 % 0.8280 %1.2780 % 0.7273 %1.4270 %