VeriEye SDK
Iris identification for stand-alone and client-server solutions
VeriEye iris identification technology is designed for biometric systems developers and integrators. The technology includes many proprietary solutions that enable robust iris enrollment under various conditions and fast iris matching in 1-to-1 and 1-to-many modes.
Available as a software development kit that allows development of stand-alone and network-based solutions on Microsoft Windows, Linux, macOS, iOS and Android platforms.
Reliability Tests
We present the testing results to show the iris liveness check reliability evaluations for the VeriEye 13.0 algorithm.
Neurotechnology's internally collected dataset was used for testing the iris liveness check algorithm. The dataset contained:
- 113,242 real samples.
- 12,098 attack samples for spoofing iris liveness check using printed photos on regular laser printer paper and photo paper.
Receiver operation characteristic (ROC) curves are usually used to demonstrate the accuracy of a biometric algorithm. A ROC curve shows the dependence of Bona fide Presentation Classification Error Rate (BPCER) on the Attack Presentation Classification Error Rate (APCER). Equal error rate (EER) is the rate at which both APCER and BPCER are equal.
| VeriEye 13.0 liveness check algorithm testing results with Neurotechnology internal dataset | |
|---|---|
| EER | 0.387 % |
| BPCER at 10 % APCER | 0.236 % |
| BPCER at 1 % APCER | 0.236 % |
| BPCER at 0.1 % APCER | 1.297 % |
| BPCER at 0.01 % APCER | 2.863 % |
