VeriLook SDK

Face identification for stand-alone or client-server applications

VeriLook facial identification technology is designed for biometric systems developers and integrators. The technology assures system performance and reliability with live face detection, simultaneous multiple face recognition and fast face 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 template verification and face liveness check reliability evaluations for the VeriLook 12.3 algorithm.

Template Verification Reliability Tests

The following public datasets were used for the VeriLook 12.3 algorithm face recognition reliability evaluations:

  • NIST Special Database 32 - Multiple Encounter Dataset (MEDS-II).
    • All full-profile face images from the dataset were removed because they are not supported by VeriLook SDK. This resulted in 1,216 images of 518 persons.
  • University of Massachusetts Labeled Faces in the Wild (LFW).
    • According to the original protocol, only 6,000 pairs (3,000 genuine and 3,000 impostor) should be used to report the results. But recent algorithms are "very close to the maximum achievable by a perfect classifier" [source]. Instead, as Neurotechnology algorithms were not trained on any image from this dataset, verification results on matching each pair of all 13,233 face images of 5,729 persons were chosen to be reported.
    • All identity mistakes, which had been mentioned on the LFW website, were fixed. Also, several not mentioned issues were fixed.
    • Some images from the LFW dataset contained multiple faces. The correct faces for assigned identities were chosen manually to solve these ambiguities.
  • CASIA NIR-VIS 2.0 Database.
    • The dataset contains face images, which were captured in visible light (VIS) and near-infrared (NIR) spectrums. According to the original protocol, VeriLook algorithm testing used VIS images as gallery, and NIR images as probe.
    • According to the original protocol, the dataset is split into two parts – View1 intended for algorithm development and View2 for performance evaluation. Neurotechnology algorithms were not trained on any image from this dataset. Only View2 part with 12,393 NIR images and 2,564 VIS images was used for face verification evaluation.
    • The non-cropped images (640 x 480 pixels) from the dataset were used for VeriLook algorithm testing.

Two experiments were performed with each dataset:

  • Experiment 1 maximized matching accuracy. VeriLook 12.3 algorithm reliability in this test is shown on the ROC charts as blue curves.
  • Experiment 2 maximized matching speed. VeriLook 12.3 algorithm reliability in this test is shown on the ROC charts as red curves.

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). Equal error rate (EER) is the rate at which both FAR and FRR are equal.

MEDS-II dataset
VeriLook ROC chart on NIST MEDS II face image dataset
Click to zoom
LFW dataset
VeriLook ROC chart on LFW face image dataset
Click to zoom
NIR-VIS 2.0 dataset
VeriLook ROC chart on CASIA NIR-VIS 2.0 face image dataset
Click to zoom
MEDS-II dataset
VeriLook ROC chart on NIST MEDS II face image dataset
LFW dataset
VeriLook ROC chart on LFW face image dataset
CASIA NIR-VIS 2.0 dataset
VeriLook ROC chart on CASIA NIR-VIS 2.0 face image dataset
VeriLook 12.3 algorithm testing results with face images from public datasets
  MEDS-II LFW NIR-VIS 2.0
Exp. 1 Exp. 2 Exp. 1 Exp. 2 Exp. 1 Exp. 2
Image count 1216 13233 14957
Subject count 518 5729 725
Session count 1 - 18 1 - 530 4
Image size (pixels) variable 250 x 250 480 x 640
Template size (bytes) 322 322 322 322 322 322
EER 0.2256 % 0.2627 % 0.0080 % 0.0147 % 0.0413 % 0.0538 %
FRR at 0.1 % FAR 0.2268 % 0.2721 % 0.0029 % 0.0041 % 0.0129 % 0.0436 %
FRR at 0.01 % FAR 0.2268 % 0.3175 % 0.0078 % 0.0194 % 0.1291 % 0.1678 %
FRR at 0.001 % FAR 0.2268 % 0.3175 % 0.0281 % 0.0454 % 0.7455 % 0.9262 %

Face Liveness Check Reliability Tests

Neurotechnology's internally collected dataset was used for testing the face liveness check algorithm. The dataset contained:

  • 27,483 real samples.
  • 18,060 attack samples, which included these scenarios for spoofing face liveness check:
    • Screen-based: phone, laptop, tablet and PC screens were used.
    • Paper photo-based: regular laser printer paper, photo paper and matte paper was used.
    • 3D mask-based: off-the-shelf carnival masks were used.

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.

VeriLook 12.3 face liveness estimation reliability
VeriLook 12.3 liveness check algorithm testing results with Neurotechnology internal dataset
EER 0.1702 %
BPCER at 10 % APCER 0.0109 %
BPCER at 1 % APCER 0.0182 %
BPCER at 0.1 % APCER 0.7606 %
Representatives
Neurotechnology Distributors Map Ex-Cle S.A - representative in Argentina FingerSec do Brasil - distributor in Brazil (web site in Portuguese) Distributors in Chile Neurotechnology's Chinese Office (web site in Chinese) Security Systems Ltda - distributor in Colombia (web site in Spanish) General Security El Salvador - distributor in El Salvador (web site in Spanish) Infokey Software Solutions - distributor in Greece (web site in Greek and English) India Branch - Neurotechnology Lab India Fulcrum Biometrics India Pvt. Ltd. - distributor in India Biometric srl - distributor in Italy (web site in Italian) Software Sources Ltd - distributor in Israel Bruce and Brian Co., LTD. - distributor in Korea (web site in Korean) Biosec Solutions - distributor in Nigeria Digital Data Systems (DDS Biometrics) - distributor in Pakistan Ex-Cle S.A - distributor in Paraguay Digital Works - distributor in Peru DigiFace Solutions - distributor in Singapore Fingerprint i.t. - distributor in South Africa Sri Lanka Branch - Neurotechnology Lab Delaney Biometrics - distributor in the UK Fulcrum Biometrics - representative in the USA
Follow us
Facebook icon   LinkedIn icon   Twitter icon   Youtube icon   Email newsletter icon
Copyright © 1998 - 2022 Neurotechnology | Terms & Conditions | Privacy Policy | Career