MegaMatcher Standard SDK and Extended SDK

MegaMatcher SDK is intended for development of large-scale AFIS or multi-biometric identification products. Face and fingerprint recognition engines are included in MegaMatcher SDK, and iris recognition engine is included in VeriEye 2.2 Standard SDK, that can be used as add-on for MegaMatcher SDK.

MegaMatcher 3.1 SDK includes server-side software and a set of modules for developing client-side applications. .NET components are included for rapid development of client-side software. MegaMatcher 3.1 supports BioAPI 2.0. To ensure system compatibility with other software, WSQ library is included, as well as modules for conversion between MegaMatcher template and biometric standards.

MegaMatcher 3.1 is suitable not only for developing civil AFIS, but also for forensic AFIS applications, as it includes an API for latent fingerprint template editing. Latent fingerprint template editing is necessary in order to submit a latent fingerprint (for example, one taken from a crime scene) for the identification into AFIS. Also MegaMatcher is able to match rolled and flat fingerprints between themselves.

Depending on the required biometric system performance, MegaMatcher 3.1 can be used in these architectures:

Single server Matches 40,000 fingerprints per second. Requires MegaMatcher Standard SDK.	PC cluster Matches from 40,000 to 8,000,000 fingerprints per second. Requires MegaMatcher Extended SDK.
Single MegaMatcher Accelerator Matches 10,000,000 fingerprints per second. Requires MegaMatcher Standard SDK for client application development and 1 MegaMatcher Accelerator unit.	MegaMatcher Accelerator Cluster Matches from 20,000,000 to 300,000,000 fingerprints per second. Requires MegaMatcher Standard SDK for client application development and multiple MegaMatcher Accelerator units for reaching the required performance.

These types of MegaMatcher 3.1 SDK are available:

• MegaMatcher 3.1 Standard SDK for developing a client/server based multi-biometric face-fingerprint and optionally iris identification product. This SDK is suitable for network-based and web-based systems with database size ranging from several thousands records up to million records. The SDK includes ready-to-use server-side software and a set of components for developing client-side applications. Also one or more MegaMatcher Accelerator units can be additionally purchased for building high performance systems that match tens of millions fingerprints per second.
• MegaMatcher 3.1 Extended SDK for developing a large-scale network-based AFIS or multi-biometric identification product. The fault-tolerant scalable cluster software allows to perform fast parallel matching, processes high number of identification requests and handles databases with practically unlimited size. The SDK includes all components of MegaMatcher 3.1 Standard SDK and ready-to-use cluster server and node software. This SDK also allows to develop network-based and web-based systems.

The table below compares MegaMatcher 3.1 Standard SDK and MegaMatcher 3.1 Extended SDK.

List of components and supported platforms

The table below explains which modules can run on the specified platforms.

MegaMatcher Cluster Server

Cluster Server licenses and software are not included in MegaMatcher 3.1 Standard SDK.

MegaMatcher Cluster Server splits the templates database and distributes it between cluster nodes.

Microsoft SQL Server, Oracle, PostgreSQL and MySQL database support modules with source codes are included for Cluster Server component. Custom modules for working with other databases can also be developed by integrator and used with MegaMatcher Cluster Server components. See the table above for details on platform compatability.

MegaMatcher Cluster Node

Cluster Node licenses and software are not included in MegaMatcher 3.1 Standard SDK.

MegaMatcher Cluster Node is a component of the cluster, which performs the actual template matching using the MegaMatcher's fused single modality and multi-biometric identification algorithm or, optionally, face or fingerprint identification engine. VeriEye 2.2 Matcher component can be run together with the MegaMatcher Cluster Node to add iris engine for template matching. Each Cluster Node performs template matching within its own part of the database. Obviously, a larger number of nodes results in faster matching, because each node operates on a smaller part of the database. Cluster Node can store templates using a database, or using RAM for achieving better performance.

Microsoft SQL Server, Microsoft Access, PostgreSQL, SQLite and MySQL support modules (with source code) are included for node component. See the table above for details on platform compatability.

MegaMatcher Server

• MegaMatcher Server runs on single PC and is intended for moderate size systems like local AFIS or multi-biometric identification system. VeriEye 2.2 Matcher component can be run together with the MegaMatcher Cluster Server to add iris engine for template matching. The Server performs the biometric template matching and provides the same functionality as MegaMatcher Cluster software, except the parallel matching ability.
• Microsoft SQL Server, Oracle, PostgreSQL and MySQL database support modules with source codes are included for Server component. Custom modules for working with other databases can also be developed by integrator and used with MegaMatcher Server component. See the table above for details on platform compatability.
• Source code of sample web server software. The software accepts biometric templates from MegaMatcher web client application, sends them to MegaMatcher Server for matching and returns matching results to the client application. The web server is stand-alone and does not require any third-party web server software (like Apache or Microsoft IIS).

MegaMatcher Client

MegaMatcher Standard and Extended SDKs include a set of modules that are intended for the development of biometric system's client-side applications. A client application gathers biometric samples, extracts biometric template information from them and sends extracted template for matching to MegaMatcher Server and/or MegaMatcher Cluster Server.

• MegaMatcher Extractor module performs fingerprint or facial image processing and extracts unique biometric features, that are sent to MegaMatcher Server or Cluster Server for identification. The Extractor module can be used with fingerprint images from fingerprint scanners and/or files and with face images from cameras and/or files.
  .NET wrapper for MegaMatcher Extractor module is included. The module is compiled in native code therefore .Net applications require a special wrapper to access module's API.
• VeriEye 2.2 Extractor component can be used for iris image processing and biometric features extraction. The iris features can be sent to MegaMatcher Server or Cluster Server for identification.
• The Client communication module allows sending a task to MegaMatcher Server, querying status of the task, getting the results and removing the task from server. This component hides all low level communications and provides high-level API for the developer.
• Fingerprint view component (.NET) shows captured fingerprint image. This component is also able to show extracted minutia points.
  
• Fingerprint segmentation module separates fingerprints if an image contains more than one fingerprint. This component enables fingerprints Neurotechnology from scanned tenprint card or image captured using scanners that allow to scan two or more fingers at once.
• Fingerprint pattern classification module allows to determine a fingerprint pattern class. The classification is usually used in forensics, but also it can 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.
• Scanners support component allows manipulating scanners that are connected to the PC. See the table above for the list of supported scanners and platform compatability.
• Camera support component allows manipulating cameras and webcams that are connected to the PC.
• 
  Click to zoom
  Latent Fingerprint Editor. 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 shows how to change minutia's coordinates, direction, type and other parameters. Sample editor is available for Microsoft .Net environment.
• NImages Pro (WSQ) library. WSQ (Wavelet Scalar Quantization) fingerprint image compression allows compressing image up to 10-15 times. WSQ compression process is "lossy", meaning that the reconstructed image isn't equal to the original (some information has been lost). However, the WSQ algorithm was specially designed to minimize the loss of fingerprint information, so that the reconstructed image is as close as possible to the original.
  MegaMatcher 3.1 SDK contains a WSQ compression and decompression library, which can be used to minimize storage size of fingerprint images and for data interchange between systems. .NET wrapper is included.
• NTFI library. Neurotechnology Token Face Image (NTFI) library is intended to provide token^* face images compatible with the Face Image Format as in ISO/IEC 19794 standard. This face image format enables range of applications on variety of devices, including devices that have limited resources required for data storage, and improves recognition accuracy by specifying data format, scene constraints (lighting, pose), photographic properties (positioning, camera focus) and digital image attributes (image resolution, image size).
  The NTFI library has the following features:
  • Token face image creation from an image containing human face using eye coordinates which may be either hand marked or detected automatically using Neurotechnology VeriLook face detection algorithm.
  • Face is detected and eye coordinates are acquired using state-of-the-art Neurotechnology VeriLook face detection and recognition algorithm.
  • Geometrical normalization of face image according to proportions and photographic properties in ISO/IEC 19794 standard.
  • Intelligent image padding algorithm for cut of parts of token face image as in ISO/IEC 19794 standard.
  • Test the created token face image for following quality criteria suggested in ISO/IEC 19794 standard:
    • Background uniformity – the background in the token face image should be uniform, not cluttered.
    • Sharpness – the token face image should not be blurred.
    • Too light or too dark images – the token face image should not be too dark or too light.
    • Exposure range of an image – the token face image should have a reasonable exposure range to represent as much details of the subject in the image as possible.
  • Evaluate token face image quality based on suggestions of ISO/IEC 19794 standard (Using the quality criteria above).
• Biometric Standard Support modules. These modules can be used for biometric data interchange between MegaMatcher and biometric systems. The following standards are supported:
  • BioAPI 2.0 (ISO/IEC 19784-1:2006) Framework and Biometric Service Provider (BSP) for face, fingerprint and iris identification engine
  • ISO/IEC 19794-2 (Information technology – Biometric data interchange formats – Part 2: Fingerprint minutiae data)
  • ISO/IEC 19794-4 (Information technology – Biometric data interchange formats – Part 4: Finger image data)
  • ISO/IEC 19794-5 (Information technology – Biometric data interchange formats – Part 5: Face image data)
  • ISO/IEC 19794-6 (Information technology – Biometric data interchange formats – Part 6: Iris Image Data)
  • ANSI/INCITS 378-2004 (Finger Minutiae Format for Data Interchange)(ANSI378)
  • ANSI/INCITS 381-2004 (American National Standard for Information Technology – Finger Image-Based Data Interchange Format)
  • ANSI/INCITS 385-2004 (American National Standard for Information Technology – Face Recognition Format for Data Interchange)
  • ANSI/INCITS 379-2004 (American National Standard for Information Technology – Iris Image Interchange Format)
  • ANSI/NIST-ITL 1-2007 (Data Format for the Interchange of Fingerprint, Facial, & Other Biometric Information - Part 1)
  .NET wrappers for each module are included.

^*Token in this context is used as "symbolic image, good enough image for machine recognition". Token Image as in ISO/IEC19794-5: "A Face Image Type that specifies frontal images with a specific geometric size and eye positioning based on the width and height of the image. This image type is suitable for minimizing the storage requirements for computer face recognition tasks such as verification while still offering vendor independence and human verification (versus human examination which requires more detail) capabilities."

Go to MegaMatcher contents

Supported fingerprint scanners under Microsoft Windows

List of scanners supported by MegaMatcher SDK under Linux is available here.

The table below explains which scanners are supported by MegaMatcher SDK under certain versions of Microsoft Windows.

(1) The list of supported OS is given only for fingerprint scanner part of the device; the device is also able to capture faces and irises.

Go to MegaMatcher contents

Supported fingerprint scanners under Linux

List of scanners supported by MegaMatcher SDK under Microsoft Windows is available here.

The table below explains which scanners are supported by MegaMatcher SDK under Linux.

Go to MegaMatcher contents