MegaMatcher SDK

Large-scale AFIS and multi-biometric identification

MegaMatcher is designed for large-scale AFIS and multi-biometric systems developers. The technology ensures high reliability and speed of biometric identification even when using large databases.

Available as a software development kit that allows development of large-scale single- or multi-biometric fingerprint, iris, face, voice or palm print identification products for Microsoft Windows, Linux, Mac OS X, iOS and Android platforms.

Reliability Tests

The identification reliability is important for large-scale systems. MegaMatcher SDK includes a fused algorithm for fast and reliable identification using several biometric records taken from the same person.

As we do not have any single database with all supported biometric modalities, separate tests with selected modalities were performed for the MegaMatcher biometric engines to demonstrate their reliability and performance with single biometric modalities and combinations of several modalities:

Fingerprint, face and iris matching engines tests

The tests with MegaMatcher biometric fingerprint, face and iris matching engines and fused template matching algorithm were performed using Neurotechnology internal multi-biometric database:

  • The database had 7,500 sets of biometric records; each set contained 1 face, 2 irises and 10 fingerprints representing a unique person.
  • 1,500 unique persons were represented in the database.
  • 5 capture sessions were performed for each person.

The tests were performed with these biometric template types:

  • 1 fingerprint record extracted from left index fingerprint image.
  • 1 face record.
  • 1 iris record extracted from left eye image.
  • 2 fingerprint records extracted from same person's left and right index fingerprint images.
  • 2 iris records extracted from same person's different eye images.
  • 1 fingerprint + 1 face records – left index fingerprint and face taken from the same person.
  • 1 face + 1 iris records – left iris and face taken from the same person.
  • 1 fingerprint + 1 iris records – left index fingerprint and left iris taken from the same person.
  • 1 fingerprint + 1 face + 1 iris records – left index fingerprint, left iris and face taken from the same person.

The biometric engines had these parameters set:

  • ±90 degrees fingerprint rotation tolerance value was used for template matching;
  • ±15 degrees iris rotation tolerance value was used for template matching.

Two tests were performed with each template type:

  • Test 1 maximized matching accuracy. MegaMatcher 10.0 fused algorithm reliability in this test is shown as blue curves on the ROC charts.
  • Test 2 maximized matching speed. MegaMatcher 10.0 fused algorithm reliability in this test is shown as red curves on the ROC charts.

The tests with templates. which contained 1 fingerprint + 1 face + 1 iris records, resulted with 0 % FRR for all FAR values

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).

1 fingerprint
ROC chart: MegaMatcher 10.0 fingerprint matching algorithm
Click to zoom
1 face
ROC chart: MegaMatcher 10.0 face matching algorithm
Click to zoom
1 iris
ROC chart: MegaMatcher 10.0 iris matching algorithm
Click to zoom
2 fingerprints
ROC chart: MegaMatcher 10.0 fused matching algorithm, 2 fingerprints in a template
Click to zoom
       
2 irises
ROC chart: MegaMatcher 10.0 fused matching algorithm, 2 irises in a template
Click to zoom
Fingerprint + face
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 fingerprint and 1 face in a template
Click to zoom
Fingerprint + iris
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 fingerprint and 1 iris in a template
Click to zoom
Face + iris
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 face and 1 iris in a template
Click to zoom
1 fingerprint
ROC chart: MegaMatcher 10.0 fingerprint matching algorithm
1 face
ROC chart: MegaMatcher 10.0 face matching algorithm
1 iris
ROC chart: MegaMatcher 10.0 iris matching algorithm
2 fingerprints
ROC chart: MegaMatcher 10.0 fused matching algorithm, 2 fingerprints in a template
2 irises
ROC chart: MegaMatcher 10.0 fused matching algorithm, 2 irises in a template
Fingerprint + face
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 fingerprint and 1 face in a template
Fingerprint + iris
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 fingerprint and 1 iris in a template
Face + iris
ROC chart: MegaMatcher 10.0 fused matching algorithm, 1 face and 1 iris in a template

MegaMatcher 10.0 template matching engines reliability testing results
A template contains these biometric records FRR at
0.001 % FAR
FRR at
0.0001 % FAR
Test 1 Test 2 Test 1 Test 2
1 fingerprint 0.0200 %0.0833 % 0.0833 %0.1167 %
1 face 4.5870 %7.0670 % 9.2000 %11.7000 %
1 iris 0.7000 %0.8967 % 1.0030 %1.1130 %
2 fingerprints 0.0000 %0.0000 % 0.0000 %0.0000 %
2 irises 0.1233 %0.1933 % 0.1500 %0.2733 %
1 fingerprint + 1 face 0.0000 %0.0000 % 0.0000 %0.0100 %
1 fingerprint + 1 iris 0.0000 %0.0000 % 0.0000 %0.0000 %
1 face + 1 iris 0.0633 %0.1400 % 0.0900 %0.2033 %
1 fingerprint + 1 face + 1 iris 0.0000 %0.0000 % 0.0000 %0.0000 %

These tests show that a large-scale automated biometric identification system based on MegaMatcher provides high identification reliability when using fingerprints, using fused same-biometric (different fingerprints or irises from the same person) matching significantly reduces FRR, and using multi-biometric identification results in a significant reliability increase, allowing the system to reach almost 0 % FRR.

Palm print engine tests

MegaMatcher Palm Print ROC chart calculated using internal palm print images database

The MegaMatcher palm print template matching algorithm reliability tests were performed using internal palm print images database. The database contained 1,993 images of right hand full palms and 1,996 images of left hand full palms. The database represented 1,000 unique persons.

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). The chart with ROC curves for the MegaMatcher palm print template matching algorithm are available on the right.