Algorithm Features and Capabilities
Download
MegaMatcher On Card SDK
brochure (PDF)
Complete information, including all technical specifications, licensing and prices.
The 23-page brochure can be printed on both Letter and A4 paper.
File size:
2.0 Megabytes;
Updated on:
April 11, 2012.
MegaMatcher On Card 3.1 is based on MegaMatcher multi-biometric AFIS technology and provides a number of advantages over a standard fingerprint / face / iris identification system or similar products for smart cards, including:
-
Accuracy.
MegaMatcher On Card provides the same level of accuracy of an AFIS (automated fingerprint identification system) in a verification process using ISO/IEC 19794-2 compact card minutiae format templates together with the security of storage of biometric templates and matching algorithm on a smart card.
Face and iris modalities on-card verification precision conforms to the large scale multi-biometric MegaMatcher SDK accuracy rates of Neurotechnology's compact format templates matching.
See the reliability testing results that compare MegaMatcher On Card with MegaMatcher 4.3.
-
Configurability.
MegaMatcher On Card fingerprint algorithm has different performance configurations that can be chosen according to the operating scenario, the requirements to matching accuracy, the smart card platform speed and memory constraints.
-
Multibiometrics.
The face and iris matching engines can be used as an additional or alternative factor of authentication that enhances the fingerprint verification.
Fingerprint, iris and face templates can be stored on a single card together with the fingerprint, iris and face matching algorithms.
Go to MegaMatcher On Card contents
Technical Specifications
MegaMatcher On Card 3.1 can be configured according to different requirements and smart card constraints, at both pure Java Card level and native code.
The summary of average memory requirements is available below.
The MegaMatcher On Card 3.1 template matching engines performance was tested for smart cards from several vendors; see the testing results for more information on matching speed for a particular card.
-
500 dpi is the recommended fingerprint image resolution.
-
640 x 480 pixels is the recommended image size for face detection.
40 pixels is the minimal distance between the eyes for face detection.
-
MegaMatcher On Card face extraction engine has certain tolerance to face posture that assures face detection:
- head roll (tilt) – ±15 degrees from frontal position.
- head pitch (nod) – ±15 degrees from frontal position.
- head yaw (bobble) – ±15 degrees from frontal position.
-
640 x 480 pixels is the minimum image size for iris capture.
±15 degrees is the default iris rotation tolerance; this value can be extended on demand.
MegaMatcher On Card 3.1 memory requirements for native level integration
(maximized accuracy configuration) |
| |
Code size (kilobytes) |
Required RAM for data (bytes) |
Template size (bytes) |
| Fingerprint verification engine |
6.0 - 8.0 |
960 - 1,400 (1) |
1,300 - 1,700 (1) |
| Face verification engine |
Not implemented |
| Iris verification engine |
| Multi-modal verification engines |
(1) Depends on the configurable maximal number of minutiae.
| MegaMatcher On Card 3.1 memory requirements for Java Card post-issuance libraries (maximized speed configuration) |
| |
Code size (kilobytes) |
Required RAM for data (bytes) |
Template size (bytes) |
| Fingerprint verification engine |
less than 13.3 |
less than 600 (1) |
less than 1,024 (1) |
| Face verification engine |
less than 4.4 |
less than 16 |
less than 2,700 (2) |
| Iris verification engine |
less than 8.3 |
less than 700 (3) |
less than 1,100 (3) |
| Bi-modal fingerprint + face verification engine |
less than 16 |
less than
600 (1) (2) |
see specific modalities above |
| Bi-modal fingerprint + iris verification engine |
less than 20 |
less than
800 (1) (3) |
see specific modalities above |
| Bi-modal face + iris verification engine |
less than 11 |
less than
700 (2) (3) |
see specific modalities above |
| Tri-modal verification engine |
less than 22 |
less than
800 (1) (2) (3) |
see specific modalities above |
(1) Depends on the configurable maximal number of minutiae.
(2) Using faces compact card template format.
(3) Using irises compact card template format.
Go to MegaMatcher On Card contents
Reliability & Performance Tests
The MegaMatcher On Card 3.1 template verification algorithm is a version of MegaMatcher 4.3 algorithm adapted to the limited computational resources of smart cards.
These tests were performed:
Reliability tests with publicly available databases for single biometric modalities
These reliability tests compare the original MegaMatcher 4.3 and the MegaMatcher On Card 3.1 algorithms for fingerprint, face and iris modalities:
-
Fingerprint verification.
The tests were performed using a subset of SONATEQ Fingerprint Database SQ FDB1-75TS1:
- only left hand's index fingerprint images were used;
- ISO/IEC 19794-2:2005 compact card minutiae format was used during testing;
- the number of minutiae was truncated to 48 in both probe and gallery compact templates prior to matching;
- ±90 degrees fingerprint rotation tolerance value was used for template matching;
- maximized accuracy and maximized speed configurations were tested.
-
Face verification.
The tests were performed using face images from XM2VTS database.
- proprietary template format was used during testing;
- maximized speed configuration was used during testing.
-
Iris verification.
The tests were performed using iris images from ND-IRIS-0405 Iris Image Dataset.
- proprietary template format was used during testing;
- maximized speed configuration was used during testing.
Receiver operation characteristics (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).
Reliability tests with an internal Neurotechnology multi-biometric database
The tests with MegaMatcher On Card biometric fingerprint, face and iris matching engines and fused template matching algorithm were performed using a 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 – taken from left index fingerprint.
- 1 face record.
- 1 iris record – taken from left eye image.
- 2 fingerprint records taken from same person's left and right index fingerprints.
- 2 iris records taken from same person's different eyes.
- 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 fingerprint template extraction and matching was performed with these settings:
- the number of minutiae was truncated to 48 in both probe and gallery compact templates prior to matching;
- ±90 degrees fingerprint rotation tolerance value was used for template matching.
These experiments were performed with the templates:
-
Experiment 1 maximized matching accuracy.
The experiment was performed only with template types that contained fingerprint records.
MegaMatcher On Card 3.1 algorithm reliability in this test is shown as blue curves on the ROC charts.
-
Experiment 2 maximized matching speed.
The experiment was performed with all template types.
MegaMatcher On Card 3.1 algorithm reliability in this test is shown as red curves on the ROC charts.
Receiver operation characteristics (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).
Matching speed tests
MegaMatcher On Card 3.1 fingerprint, face and iris matching algorithms were tested on smart cards from several vendors.
The matching speeds are available below.
Please contact us to get more information about the expectations on a specific platform on which you intend to use it.
| MegaMatcher On Card 3.1 average template verification time (seconds) |
| Smart card model |
Fingerprints (1) |
Faces (2) |
Irises (2) |
Atmel AT90SC28872RCU
(native level, maximized accuracy configuration) |
0.094 |
- |
- |
ATHENA IDProtectV2
(post-issuance application, maximized speed configuration) |
0.674 |
0.503 |
0.387 |
NXP P5CC0037
(native level, maximized accuracy configuration) |
1.114 |
- |
- |
JCOP 2.4.1 R2
(post-issuance application, maximized speed configuration) |
3.714 |
1.179 or 1.600 |
1.281 or 1.511 |
JCOP 2.4.1 R3
(post-issuance application, maximized speed configuration) |
1.945 |
1.423 |
1.054 |
Samsung S3CC91C
(native level, maximized accuracy configuration) |
0.548 |
- |
- |
(1)
Performance depends on the maximal number of minutiae features within enrolled and verified fingerprint templates.
Results correspond to matching test of an enrolled and verified templates each containing 48 minutiae.
Contact SCR335 USB smart card reader was used for PC/SC communication.
(2)
Performance depends on the baud rate of protocol and APDU type chosen.
Results correspond to matching face and iris compact card format templates using short length field APDUs.
Timings are available either for both contactless and contact or contact only interface tests.
SCR335 and OMNIKEY 5321 USB smart card readers were used for contact or contactless test respectively.
Go to MegaMatcher On Card contents
|
