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.

Fingerprint Components

MegaMatcher SDK includes the following biometric components for fingerprint image capture and segmentation, fingerprint template extraction and matching, as well as biometric standards and specific image format support.

Fingerprint Matcher component

The Fingerprint Matcher performs fingerprint template matching in 1-to-1 (verification) and 1-to-many (identification) modes. Also the Fingerprint Matcher component includes fused matching algorithm that allows to increase template matching reliability by:

  • matching templates that contain 2 or more fingerprint records (note that Fingerprint Segmenter or Fingerprint Client components are required to perform template extraction from images that contain more than one fingerprint);
  • matching templates that contain fingerprint, face, voiceprint and/or iris records (note that matching faces, irises and voiceprints requires to purchase Face Matcher, Iris Matcher and Voice Matcher components correspondingly).

The Fingerprint Matcher component matches 40,000 fingerprints per second and is designed to be used in desktop or mobile biometric systems, which run on PCs or laptops with at least Intel Core 2 Q9400 (2.67 GHz) processor.

One Fingerprint Matcher license is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Embedded Fingerprint Matcher component

The Embedded Fingerprint Matcher has the same functionality, as the Fingerprint Matcher. It matches 3,000 fingerprints per second and is designed to be used in embedded or mobile biometric systems, which run on ARM Linux or Android or iOS devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz).

One Embedded Fingerprint Matcher license for each of Android, iOS and ARM Linux platforms is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fast Fingerprint Matcher component

The Fast Fingerprint Matcher has the same functionality, as the Fingerprint Matcher. It matches 200,000 fingerprints per second and is designed for large-scale AFIS and biometric systems, which run on high-end PCs or servers hardware with at least Intel Core i7-4771 (3.5 GHz) processor.

Multi-biometric fused template matching can be achieved by combining the Fast Fingerprint Matcher component with Face, Voice and/or Iris Matchers (regular or fast versions of them can be used depending on project implementation).

One Fast Fingerprint Matcher license is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fingerprint Client component

The Fingerprint Client component is a combination of the Fingerprint Extractor, Fingerprint BSS, Fingerprint Segmenter and Fingerprint WSQ components. It is intended for the systems that need to support most or all functionality of the mentioned components on the same PC. Using these licenses allows to optimize component license costs as well as reduce license management.

The Fingerprint Client extracts a single fingerprint template in 0.6 seconds. The specified performance requires a PC or laptop with at least Intel Core 2 Q9400 (2.67 GHz) processor.

Three licenses for the Fingerprint Client component are included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Embedded Fingerprint Client component

The Embedded Fingerprint Client component has the same functionality, as the Fingerprint Client component and is designed to be run on ARM Linux or Android or iOS devices. The Android devices should based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single fingerprint template in 1.2 seconds.

Three licenses for the Embedded Fingerprint Client component for each of Android, iOS and ARM Linux platforms are included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fingerprint Extractor component

Fingerprint Extractor creates fingerprint templates from fingerprint images. Fingerprint templates can be stored in the following formats by the Fingerprint Extractor component:

  • Neurotechnology proprietary fingerprint template format;
  • ISO/IEC 19794-2:2005 with Cor. 1:2009 (General and On-Card Fingerprint Minutiae Data Formats);
  • ISO/IEC 19794-2:2011 with Cor. 1:2012 (General and On-Card Fingerprint Minutiae Data Formats);
  • ANSI/INCITS 378-2004 (Finger Minutiae Format for Data Interchange);
  • ANSI/INCITS 378-2009 with Amd. 1:2010 (Finger Minutiae Format for Data Interchange).

Proprietary image quality control may be applied to accept only good quality fingerprint images.

The Fingerprint Extractor can generalize a fingerprint template from several images that contain the same fingerprint to improve the template's quality.

The component extracts a single fingerprint template in 1.34 seconds. The specified performance requires a PC or laptop with at least Intel Core 2 Q9400 (2.67 GHz) processor.

One Fingerprint Extractor license is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Embedded Fingerprint Extractor component

The Embedded Fingerprint Extractor has the same functionality as the Fingerprint Extractor and is designed to be run on ARM Linux or Android or iOS devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single fingerprint template in 1.34 seconds.

One Embedded Fingerprint Extractor license for each of Android, iOS and ARM Linux platforms is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fast Fingerprint Extractor component

The Fast Fingerprint Extractor has the same functionality as the Fingerprint Extractor and is designed to be used in high-volume server applications, which run on server hardware with at least dual Intel Xeon E5-2680V2 (2.8 GHz) processors. The component performs template extraction at a speed of 3,000 fingerprints per minute.

One Fast Fingerprint Extractor license is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fingerprint Capturer component

Fingerprint Capturer component is designed for using in systems which acquire fingerprint images from fingerprint readers on client side and send them to a server running Fast Fingerprint Extractor component for further processing.

The Fingerprint Capturer component also includes:

  • JPEG 2000 image format support module with 1000 ppi Fingerprint Profile;
  • NFIQ algorithm module, which uses a standard method to determine fingerprint image quality.
  • WSQ image format support module, which allows to compress a fingerprint image up to 10-15 times. The module functionality is identical to Fingerprint WSQ.

Three Fingerprint Capturer licenses are included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Embedded Fingerprint Capturer component

The Embedded Fingerprint Capturer has the same functionality as the Fingerprint Capturer and is designed to be run on ARM Linux or Android or iOS devices.

Three Embedded Fingerprint Capturer licenses for each of Android, iOS and ARM Linux platforms are included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fingerprint Segmenter component

The Fingerprint Segmenter components separates fingerprints if an image contains more than one fingerprint. This component enables Fingerprint Extractor component to process fingerprints from scanned tenprint card or image captured using scanners that allow to scan two or more fingers at once.

Fingerprint pattern classification module that allows to determine a fingerprint pattern class is included with Fingerprint Segmenter component. The classification is usually used in forensics, but it also may be used to increase fingerprint matching speed. The defined classes are:

  • Left Slant Loop;
  • Right Slant Loop;
  • Tented Arch;
  • Whorl;
  • Scar;
  • "Unknown" – for the nondetermined classes.

The Fingerprint Segmenter is designed for desktop or mobile applications that run on PC or laptop with at least Intel Core 2 Q9400 (2.67 GHz) processor. It can be used from C/C++, C# and Java applications on all supported platforms. .NET wrappers of Windows libraries are provided for .NET developers.

The Fingerprint Segmenter licenses can be purchased anytime by MegaMatcher 9.0 SDK customers.

Fast Fingerprint Segmenter component

The Fast Fingerprint Segmenter has the same functionality as the Fingerprint Segmenter and is designed to be used in high-volume server applications, which run on server hardware with at least dual Intel Xeon E5-2680V2 (2.8 GHz) processors.

One Fast Fingerprint Segmenter license is included with MegaMatcher 9.0 Standard SDK and MegaMatcher 9.0 Extended SDK. More licenses for this component can be purchased any time by MegaMatcher 9.0 SDK customers.

Fingerprint BSS (Biometric Standards Support) component

The Fingerprint BSS component allows to integrate support for fingerprint template and image format standards and additional image formats with new or existing biometric systems based on MegaMatcher SDK.

These biometric standards are supported by the Fingerprint BSS component:

  • BioAPI 2.0 (ISO/IEC 19784-1:2006) (Framework and Biometric Service Provider for fingerprint identification engine)
  • CBEFF V1.2 (ANSI INCITS 398-2008) (Common Biometric Exchange Formats Framework)
  • CBEFF V2.0 (ISO/IEC 19785-1:2006, 19785-3:2007) (Common Biometric Exchange Formats Framework)
  • ISO/IEC 19794-4:2005 with Cor. 1:2011 (Finger Image Data)
  • ISO/IEC 19794-4:2011 with Cor. 1:2012 (Finger Image Data)
  • ANSI/INCITS 381-2004 (Finger Image-Based Data Interchange Format)
  • ANSI/INCITS 381-2009 with Amd. 1:2011 (Finger Image-Based Data Interchange Format)
  • ANSI/NIST-CSL 1-1993 (Data Format for the Interchange of Fingerprint, Facial, & SMT Information)
  • ANSI/NIST-ITL 1a-1997 (Data Format for the Interchange of Fingerprint, Facial, & SMT Information)
  • ANSI/NIST-ITL 1-2000 (Data Format for the Interchange of Fingerprint, Facial, & SMT Information)
  • ANSI/NIST-ITL 1-2007 (Data Format for the Interchange of Fingerprint, Facial, & Other Biometric Information)
  • ANSI/NIST-ITL 1a-2009 (Data Format for the Interchange of Fingerprint, Facial, & Other Biometric Information)

The Fingerprint BSS component allows conversion between Neurotechnology proprietary fingerprint templates, ISO/IEC 19794-2:2005, ISO/IEC 19794-2:2011, ANSI/INCITS 378-2004, ANSI/INCITS 378-2009 and ANSI/NIST-ITL templates.

The Fingerprint BSS component also includes:

  • JPEG 2000 image format support module with 1000 ppi Fingerprint Profile;
  • NIST IHead image format support module;
  • module with NIST Fingerprint Image Quality (NFIQ) algorithm, a standard method to determine fingerprint image quality.

Latent Fingerprint Editor is available with Fingerprint BSS component. In most cases automated image processing is unable to extract all minutiae or extracts a lot of false minutiae from latent fingerprint image (for example, taken from the crime scene). Therefore, an expert should manually edit a fingerprint template in order to submit it to an AFIS for the identification.
Sample latent fingerprint template editor (.NET) shows how to change minutia's coordinates, direction, type and other parameters.

The component is designed for applications that run on hardware with at least Intel Core 2 Q9400 (2.67 GHz) processor. It can be used from C/C++, C# and Java applications on all supported platforms. .NET wrappers of Windows libraries are provided for .NET developers.

Licenses for the Fingerprint BSS component can be purchased anytime by MegaMatcher 9.0 SDK customers.

Fingerprint WSQ component

The Fingerprint WSQ component allows to integrate support for WSQ (Wavelet Scalar Quantization) image format. The WSQ format allows to compress a fingerprint image up to 10-15 times. WSQ compression process is "lossy", meaning that the reconstructed image is not equal to the original (some information is lost). However, the WSQ algorithm was specially designed to minimize the loss of fingerprint information therefore the reconstructed image is as close as possible to the original.

Neurotechnology's implementation of WSQ 3.1 fingerprint image compression was certified by the FBI as compliant with the accuracy requirements in the Wavelet Scalar Quantization (WSQ) Gray-Scale Fingerprint Image Compression Specification, Version 3.1.

The component is designed for applications that run on hardware with at least Intel Core 2 Q9400 (2.67 GHz) processor. It can be used from C/C++, C# and Java applications on all supported platforms. .NET wrappers of Windows libraries are provided for .NET developers.

Licenses for the Fingerprint WSQ component can be purchased anytime by MegaMatcher 9.0 SDK customers.