Smart card multi-biometrics

MegaMatcher On Card SDK offers matching-on-card technology that stores a person's fingerprint, iris and face templates on a smart card and performs template matching in a microprocessor embedded in the card, instead of matching biometric information on a PC processor.
The match-on-card method ensures that personal biometric information does not transfer to an external computer as it would in a more basic template-on-card system.

NIST MINEX-compliant fingerprint engine
PC-like verification accuracy
Configurable verification modes
Security and privacy
Multi-biometrics support
ISO/IEC standards support
Easy integration with existing systems
Different smart card platforms supported

SDK Contents

The table below lists the components of MegaMatcher On Card 11.0 SDK:

Programming samples
Components	Microsoft Windows (32 & 64 bit)	Linux (32 & 64 bit)	Mac OS X (32 & 64 bit)	Android (32 & 64 bit)	JavaCard OS
• Smart card with fingerprint matching engine					2 smart cards
• Smart card with multi-modal fingerprint, face and iris matching engine					1 smart card
• Fingerprint Card Extractor	2 single computer licenses
• Face Card Extractor	1 single computer license
• Iris Card Extractor	1 single computer license
• Library for communication with a smart card
• Device manager library
• C#
• Visual Basic .NET
• Java
• JavaCard (enrollment and verification applets)
Programming tutorials
• C
• C
• C#
• Visual Basic .NET
• Java
• JCDKv2.2.2 apdutool
• NXP JCOP tools JCShell
Documentation
• MegaMatcher On Card SDK documentation

MegaMatcher On Card fingerprint matching engine

MegaMatcher On Card 11.0 fingerprint matching engine performs fingerprint template matching in 1-to-1 mode (verification). Being based on the MegaMatcher technology, the engine is tolerant to fingerprint rotations, translations and deformations.

MegaMatcher On Card face matching engine

MegaMatcher On Card 11.0 face matching engine performs face template matching in 1-to-1 mode (verification).

MegaMatcher On Card iris matching engine

MegaMatcher On Card 11.0 iris matching engine performs iris template matching in 1-to-1 mode (verification).

Fingerprint Card Extractor component

Fingerprint Card Extractor creates ISO/IEC 19794-2 on-card comparison format fingerprint templates from fingerprint images.

Face Card Extractor component

Face Card Extractor creates face templates in proprietary on-card comparison format from face images. The Extractor can generalize a face template from several face images to improve the template's quality. The algorithm has also the ability to recognize whether a face in a video stream belongs to a real human or is a photo, in order to improve the overall security of the system.

Iris Card Extractor component

Iris Card Extractor creates iris templates in proprietary on-card comparison format from eye images.

Device Manager

Device Manager software allows to capture data from supported fingerprint readers, iris scanners, cameras and webcams. Integrators can also write plug-ins to support their fingerprint readers, cameras or other devices using the plug-in framework provided with the Device Manager.

Tech Specs

MegaMatcher On Card 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 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 ppi 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.

Below are provided the memory requirements for the native level integration and Java Card post-issuance libraries. Note that the Java Card post-issuance libraries utilize Java level RAM for internal matching engine routines, whereas the native level integrations temporary utilize RAM available at the native level while the internal routines run, thus consuming no static Java level RAM.

MegaMatcher On Card (Current Version) memory requirements for native level integration (maximized accuracy configuration)
	Code size (kilobytes)	Required RAM (bytes)	Template size (bytes)
Fingerprint verification engine	6.1 - 11.0	960 - 2,200 ⁽¹⁾	660 - 2,100 ⁽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 (Current Version) memory requirements for Java Card post-issuance libraries (maximized speed configuration)
	Code size (kilobytes)	Required RAM (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.