Content of this page

• Overview
• MegaMatcher SDK and Light SDK
• MegaMatcher Cluster Server
• MegaMatcher Cluster Node
• MegaMatcher Server
• MegaMatcher Client
• Supported development environments
• System requirements
• SDK trial
• Ordering
  

MegaMatcher, Large Scale AFIS SDK with Multi-Modal Biometric Support.

MegaMatcher SDK is intended for development of large-scale AFIS or multi-biometric face-fingerprint identification products.

The MegaMatcher multi-biometric SDK  ensures high reliability and speed of biometrical identification even when using large databases. High productivity and efficiency are supported by a fused algorithm that contains fingerprint and facial recognition engines. Integrators can use the fused algorithm for better identification results or any of these engines separately. MegaMatcher 2.0 fingerprint engine has received NIST MINEX Certification.

MegaMatcher 2.0 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. To ensure system compatibility with other software, WSQ library is included, as well as modules for conversion between MegaMatcher template and biometrical standards (ANSI/NIST ITL-1-2000, ANSI/INCITS 378-2004 and ISO/IEC 19794-2).

MegaMatcher 2.0 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. 

All components of MegaMatcher 2.0 SDK may be used on both Linux and Microsoft Windows operating systems.

MegaMatcher 2.0 SDK and Light SDK

There are these types of MegaMatcher 2.0 SDK: 

• MegaMatcher 2.0 Light SDK for developing a client/server based multi-biometric face-fingerprint 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.

• MegaMatcher 2.0 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 2.0 Light SDK and ready-to-use cluster server and node software. This SDK also allows to develop network-based and web-based systems.

The chart below shows a typical multi-biometrical identification system, developed with MegaMatcher 2.0 SDK:

A system, based on MegaMatcher 2.0 Light SDK

A system, based on MegaMatcher 2.0 SDK

The table below compares MegaMatcher 2.0 SDK and MegaMatcher 2.0 Light SDK.

List of components, supported scanners and platforms

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

MegaMatcher Cluster Server 

MegaMatcher 2.0 Cluster Server licenses and software are not included in MegaMatcher 2.0 Light SDK.

Cluster is a set of software and hardware components which solves a problem of computing power deficiency. For example, there is a task to identify a person using a database with 100 millions biometrical records. A stand-alone PC with a 3GHz processor and appropriate automated biometrical identification software will need 5-60 minutes to match this person. A cluster-based system of 10 PCs will need approximately 10 times less time to do that, 100 PCs - 100 times less time and so on.

Generally, the cluster-based automated biometrical identification system takes a template with person's biometric data and searches for the person in the database of templates. There are two possible results of the search: a set of templates matched against the given template, or affirmation that the given template doesn't match any entry in the database.

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

Microsoft SQL Server, Oracle 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 

MegaMatcher 2.0 Cluster Node licenses and software are not included in MegaMatcher 2.0 Light SDK.

MegaMatcher Cluster Node is a component of the cluster, which performs the actual template matching using the MegaMatcher's fused face-fingerprint identification algorithm or, optionally, face or fingerprint identification engine. 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, 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 intented for moderate size systems like local AFIS or multi-biometric identification system. The Server performs the biometrical template matching and provides the same functionality as MegaMatcher Cluster software, except the parallel matching ability.
• Microsoft SQL Server, Oracle 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 web server software. The software accepts biometrical 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 SDK includes a set of modules that are intended for the development of biometrical system's client-side applications. A client application gathers biometrical samples, extracts biometrical 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 biometrical features, that are sent to MegaMatcher Server or Clister 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.
• 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.
• Sample MegaMatcher web application provides user interface via Microsoft Internet Explorer browser. It contains client components written on Visual Basic 6.
• 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 allows to scan a tenprint card and enrol all fingerprints simultaneously or use 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 (.NET) allows manipulating scanners that are connected to the PC. See the table above for the list of supported scanners and platform compatability.
  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 2.0 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.
• Template Conversion modules. MegaMatcher Template Conversion modules can be used for biometric data interchange between MegaMatcher Template and biometrical standard templates. The following standards are supported:
  • ANSI/NIST-ITL 1-2000 (Data format interchange of Fingerprint, Facial, and Scar Mark and Tattoo (SMT) Information) (AN2K);
  • ANSI/INCITS 378-2004 (Finger Minutiae Format for Data Interchange)(ANSI378);
  • ISO/IEC 19794-2 (Fingerprint minutiae data).
  MegaMatcher Template Conversion modules can also be used to edit ANSI378 and ISO/IEC 19794-2 standard templates.
  .NET wrappers for each module are included.

Supported development environments

These development environments are supported:

• Microsoft Visual Studio 2005 SP1 (or newer) for Microsoft Windows platform
• GNU C compiler for Linux platform

System requirements

System requirements for Server and Cluster:

• PC with x86 compatible CPU (32bit and 64bit processors are supported, Pentium4 2GHz processor or better is recommended)
• TCP/IP network support
• Linux specific requirements:
  • Linux 2.6 or newer
  • GCC-4.0.x or newer
  • pkg-config-0.21 or newer
  • GNU Make 3.81 or newer
  • MySQL or Oracle server (Oracle for x86-64 and any other DB servers require a custom support module to be developed by the integrator)
  • GTK+ 2.10.x or newer libs and dev packages
  • libtiff-3.8.x or newer libs and dev packages
• Microsoft Windows specific requirements:
  • Microsoft Windows 2000/XP/2003/Vista (32bit or 64bit versions)
  • Microsoft SQL Server, MySQL or Oracle server (Oracle for x86-64 and any other DB servers require a custom support module to be developed by the integrator)

System requirements for client components:

• PC with x86 compatible CPU (32bit and 64bit processors are supported, Pentium4 2GHz processor or better is recommended)
• TCP/IP network support
• Linux specific requirements:
  • Linux 2.6 or newer
  • GCC-4.0.x or newer
  • GNU Make 3.81 or newer
• Microsoft Windows specific requirements:
  • Microsoft Windows 2000/XP/2003/Vista (32bit or 64bit versions)
  • Microsoft .NET framework 2.0 (for .NET components)
  • Microsoft Visual Studio 2005 SP1 or newer (for application development)
  • Microsoft Visual C++ 2005 SP1 runtime (for running a developed application)

SDK trial

Neurotechnologija offers a 30 day trial of MegaMatcher 2.0 SDK that allows to explore SDK possibilities and to try it in real environment and real application. Constant Internet connection is required during evaluation.
MegaMatcher 2.0 SDK trial is available for downloading .

Ordering

• Licensing model
• Prices
• Order