MegaMatcher SDK - Extended Edition

Large Scale AFIS and multi-biometric identification

Click Here to download the full MegaMatcher SDK brochure as a .pdf document

MegaMatcher technology is intended for large-scale AFIS and multi-biometric systems developers. The technology ensures high reliability and speed of biometric identification even when using large databases.

MegaMatcher is available as a software development kit that allows development of large-scale single- or multi-biometric fingerprint, iris, face or palm print identification products for Microsoft Windows, Linux and Mac OS X platforms.

Advantages of MegaMatcher

• Proven in national-scale projects, including passport issuance and voter deduplication.
• NIST MINEX-compliant fingerprint engine,
  NIST IREX proven iris engine.
• 200,000,000 irises or 100,000,000 fingerprints per second can be matched using MegaMatcher Accelerator.
• Fingerprint and faces can be matched on smart card using MegaMatcher On Card.
• Includes fingerprint, iris, face and palm print modalities.
• Rolled, flat and latent fingerprint matching.
• BioAPI 2.0 and other ANSI and ISO biometric standards support.
• Multiplatform, scalable cluster architecture for parallel matching.
• Effective price/performance ratio, flexible licensing and free customer support.

MegaMatcher Technology and SDK

• Requirements for large-scale biometric systems. Large-scale automatic biometric identification systems have a number of special requirements which are different from those of small- or medium-scale biometric systems. These requirements include system reliability, productivity, scalability, etc… Read more
  
• MegaMatcher SDK and MegaMatcher Accelerator in high productivity biometric systems. MegaMatcher SDK and MegaMatcher Accelerator include cluster software that allows to scale up the AFIS or multi-biometric systems to reach the required response time, database capacity and system robustness… Read more
• MegaMatcher Standard and Extended SDK. The Standard SDK is intended for development of client/server-based multi-biometric fingerprint, face, iris and palmprint identification products. The Extended SDK is intended for developing large-scale cluster-based AFIS or multi-biometric identification products … Read more
• Supported fingerprint scanners. More than 70 fingerprint scanners models are supported by MegaMatcher SDK … Read more
• Supported face capture cameras. A number of face capture cameras and web cams are supported by MegaMatcher SDK … Read more
• Supported iris scanners. A number of iris capture cameras and multi-modal face-iris devices are supported by MegaMatcher SDK … Read more
• System requirements and supported development environments. Components of MegaMatcher SDK can be run on computers with x86 32 and 64 bit processors (at least 2 GHz processor recommended). Windows, Linux and Mac OS X platforms are supported. Microsoft SQL Server, MySQL, SQLite, PostgreSQL and Oracle are supported… Read more
• Technical specifications. The MegaMatcher fingerprint engine is able to match up to 160,000 fingerprints per second, 1,200,000 faces per second or 1,440,000 irises per second on a single PC; several PCs can be connected together to form a cluster for higher performance … Read more.
• Reliability and performance testing results. MegaMatcher provides high identification reliability using either fingerprint, face or iris matching engines, and using fused single- or multi-biometric identification allows it to reach almost 0 % FRR… Read more.
• MINEX Certification. In 2007 MegaMatcher 2.0 fingerprint technology received full MINEX Certification. NIST certified MegaMatcher for use in personal identity verification program (PIV) applications… Read more
• Download. MegaMatcher brochure, fingerprint, face and iris algorithm demo applications and MegaMatcher 30-day SDK Trial are available for downloading.
  

Back to top of this page

Requirements for large-scale biometric systems

Today the need for automated biometric identification systems is increasing in civil and forensic fields of applications. Fast and accurate identification becomes particularly critical for large-scale applications, such as passport and visa documentation, border crossings, election control systems, credit card transaction control and crime scene investigations. Many countries, including the US, European countries and others, incorporate biometric data into passports, ID cards, visas and other documents for use in large national-scale automatic biometric identification systems.

Automated fingerprint identification systems (AFIS) have been widely used in forensics for the past two decades, and recently they have become relevant for civil applications as well. Whereas large-scale biometric applications require high identification speed and reliability, multi-biometric systems that incorporate both face and fingerprint recognition offer a number of advantages for improving identification quality and usability.

Large-scale automatic biometric identification systems have a number of special requirements, which are different from those for small- or middle-scale biometric systems:

The system must perform reliable identification with large databases, as biometric identification systems tend to accumulate False Acceptance Rate with database size increase and using a single fingerprint, face or iris image for identification becomes unreliable for a large-scale application. Several fingerprint images from person's different fingers or iris images from person's two eyes may be taken to increase matching reliability. Also, multi-biometric technologies (i.e. collecting fingerprint, face and/or iris samples from the same person) can be employed for greater reliability. A fused algorithm is used to create a single identification decision based on the results of those measurements.

The system must show high productivity and efficiency, which correspond to its scale: System scalability is important, as the system might be extended in the future, so a high productivity level should be kept by adding new units to the existing system. The daily number of identification requests could be very high. Identification requests should be processed in a very short time (ideally in real time), thus high computational power is required. Support for large databases (tens or hundreds of millions of records) is required. General system robustness. The system must be tolerant to hardware failures, as even temporary pauses in its work may cause big problems taking into account the application size. The system must support major biometric standards. This should allow using the system-generated templates or databases with systems from other vendors and vice versa. The system may need to match flat (plain) fingerprints with rolled fingerprints, as many institutions collect rolled fingerprint databases. The system must be able to work in the network, as in most cases client workstations are remote from the server with the central database. A forensic system must be able to edit latent fingerprint templates in order to submit latent fingerprints into the AFIS for the identification. Despite all these requirements, the system price should be as low as possible. Many existing AFIS are specialized for criminalistics or other particular applications and are quite expensive. Neurotechnology offers MegaMatcher SDK that includes technology and solutions for large-scale AFIS or multi-biometric fingerprint, iris, face and palm print identification products. MegaMatcher SDK meets all of the requirements mentioned above, for a competitive price.

Back to top of this page

MegaMatcher and MegaMatcher Accelerator in High Productivity Systems

Different large-scale biometric projects may require specific system performance. These matching engines and architectures may be used depending on the required matching speed, database size and system availability:

• Single Matching Server;
• Cluster of PCs running MegaMatcher components;
• Single MegaMatcher Accelerator 3.0 Standard or Extended unit;
• Cluster of MegaMatcher Accelerator 3.0 Standard or Extended units.

The charts below compare the different architectures for high performance AFIS or multi-biometric systems.

It is possible to use more than one architecture within a large-scale biometric system to reach optimal system performance and/or availability. For example, MegaMatcher Accelerator 3.0 unit(s) can be used for candidates selection using irises or several fingerprints, and then the results can be validated on Matching Server or Cluster with other biometric modalities. Also, two or more Clusters Servers or MegaMatcher Accelerator 3.0 clusters can be connected together for high availability system.

Single Matching Server

The architecture with a single Matching Server is intended to be used in moderate size systems like local AFIS or multi-biometric system which do not have strict requirements on performance or availability. The Matching Server software is available in MegaMatcher 4.0 Standard and Extended SDKs, as well as in VeriFinger 6.3 Extended SDK, VeriLook 5.0 Extended SDK and VeriEye 2.3 Extended SDK.

A PC running Matching Server software accepts identification requests from client-side components for fingerprint, face and/or iris biometrics and returns back the identification results. Up to 160,000 fingerprints or 1,200,000 faces or 1,440,000 irises per second can be matched on single Matching Server (on Intel Core2 processor with 4 cores running at 2.66 GHz).

The Matching Server can be also used for multi-biometric systems that use any combination of these biometric modalities: fingerprints, faces and/or irises.

Cluster of PCs running MegaMatcher components

This architecture is designed for high productivity AFIS or multi-biometric system with millions of biometric templates stored in the database. The Cluster Server component is available in MegaMatcher Extended SDK.

Cluster Server distributes identification task over computers connected to the network. A biometric system based on Cluster Server software can be scaled up anytime to meet changing project requirements in increasing user amount or request environment. The cluster software consists of a Cluster Server and software for cluster nodes that run fingerprint, face and/or iris components.

The Cluster Server accepts requests from client side, manages cluster work, distributes tasks over cluster nodes, collects results, reports them back to client side. Also it communicates with the main database which stores the biometric data.

Each cluster node matches up to 160,000 fingerprints or 1,200,000 faces or 1,440,000 irises per second (on Intel Core2 processor with 4 cores running at 2.66 GHz). The Cluster Server can be also used for multi-biometric systems that use any combination of these biometric modalities: fingerprints, faces and/or irises.

A cluster node contains part of the main database, performs identification tasks in it and reports results to the Cluster Server. The node must have enough memory to store that database part, as all data is kept in memory during identification to achieve the best matching speed. A larger number of nodes results in faster matching, because each node operates on a smaller part of the database.

The cluster node uses database to store its database part and in order to perform relational queries, such as filter persons by gender, age, living place.

The amount of required cluster nodes is calculated is this way:

1. The whole database should fit into nodes memory (RAM). For example, if there are 10GB of biometric data and each node has 2GB of free memory available, at least 5 nodes should be used as otherwise the database will not fit into nodes memory and the cluster will not work.
2. The identification speed should satisfy project requirements. The speed requirements may be defined indirectly via identification request response time and/or peak hour request quantity with a given database.
   • Response time. For example, a database stores biometric data for 1 million people with 2 fingerprints for each of them, and the response time for an identification request should be 1 second. At least 13 cluster nodes should be used to provide the required response time.
   • Peak hour request quantity. For example, the project with the same database as above requires to process 5,000 identification requests at the peak hour. At least 18 cluster nodes should be used to provide the required peak hour availability.

Two methods of node fault tolerance are implemented in Cluster Server software:

1. Spare nodes (enabled by default). A spare node "waits" until an operating node fails and is used to replace the failed one by copying the part of database that was used in the failed node. If the failed node restored, it become the spare node.
2. Re-split tasks and database over existing nodes. If a node fails, the system finishes all tasks which are not related with the failed node, reinitializes nodes again by re-splitting the database over them and continues tasks passed into cluster. As a result the overall cluster performance decreases but the cluster continues to operate until the failed node is fixed or replaced.
   Note, that the database re-split is possible only if total amount of memory available in the remaining nodes is larger than the database size.

We recommend to leave at least 10%-20% free memory reserve when calculating the amount of used nodes in a cluster for both fault tolerance methods. The memory reserve would allow to avoid situations when the system can not continue work as it has not enough resourses.

Single MegaMatcher Accelerator 3.0 Standard or Extended unit

MegaMatcher Accelerator 3.0 is a solution for large-scale AFIS and multi-biometric projects and is available in two versions:

• MegaMatcher Accelerator 3.0 Standard is intended for biometric identification projects with up to several million people enrolled in database. This version includes ready-to-use server-side fingerprint and/or iris matching software for installation on a PC with Intel Core i7 processor and 12 GB of RAM. A single MegaMatcher Accelerator 3.0 Standard unit can store 3,000,000 fingerprints or 6,000,000 irises and matches 35,000,000 fingerprints or 70,000,000 irises per second. 
• MegaMatcher Accelerator 3.0 Extended is a solution for national-scale biometric identification projects with millions of people enrolled in database. This version includes ready-to-use HP Proliant server hardware with pre-installed OS and fingerprint and/or iris matching software. A single MegaMatcher Accelerator 3.0 Extended unit can store 30,000,000 fingerprints or 50,000,000 irises and matches 100,000,000 fingerprints or 200,000,000 irises per second.
  

A MegaMatcher Accelerator 3.0 unit accepts identification requests from PCs that run client-side software based on components for fingerprint, iris or face biometrics, performs identification and returns back the results.

MegaMatcher Accelerator can be also used as a part of scalable multi-biometric identification system that uses fingerprint, face and/or iris modalities. The fingerprints and/or irises would be matched using MegaMatcher Accelerator(s), whereas other modalities would be matched using Matching Server or Cluster Server software depending on project size and performance requirements. Also MegaMatcher Accelerator 3.0 software includes fingerprint, face and iris matching engines that may be used for results validation after fast fingerprint or iris matching inside the Accelerator unit instead of using MegaMatcher Server or Cluster.

Cluster of MegaMatcher Accelerator 3.0 Standard or Extended units

MegaMatcher Accelerator 3.0 Standard and Extended versions already include cluster software, thus multiple MegaMatcher Accelerator 3.0 Standard or Extended units can be connected via network to a cluster.

To create a cluster, one MegaMatcher Accelerator unit is assigned as a primary unit in the cluster while other MegaMatcher Accelerator units act as cluster nodes. Note that the primary unit of MegaMatcher Accelerator cluster will still perform fast fingerprint and/or iris matching while using only a small part of its resources for managing the cluster.

Each MegaMatcher Accelerator 3.0 Standard unit in the cluster matches 35 millions fingerprints or 70 millions irises per second, and each MegaMatcher Accelerator 3.0 Extended unit matches 100 millions fingerprints or 200 millions irises per second.

When started, the primary unit splits the whole biometric database, which is stored on its hard disk, and send parts of the database to all MegaMatcher Accelerators in the cluster. Later the primary unit waits for fingerprint and/or iris identification requests from client side, then distributes the identification request to the units of the cluster and returns the identification results to the client side.

The cluster of MegaMatcher Accelerators can be scaled up anytime to meet changing project requirements in increasing user amount or request environment. A larger number of MegaMatcher Accelerator units results in faster matching and higher number of requests processed, because each unit operates on a smaller part of the database.

For example, there is a database with 10 million people biometric data (4 fingerprints for each user, 40 million fingerprints in total). The amount of required MegaMatcher Accelerator units is calculated is this way:

1. The whole database should fit into memory of the MegaMatcher Accelerator units. A single MegaMatcher Accelerator 3.0 Extended unit stores 30 million fingerprints, thus 2 units required to store the sample 40 million fingerprints database.
2. The response time for an identification request should satisfy project requirements. For example, the project requires receive an answer to an identification request in 1 second. Single MegaMatcher Accelerator 3.0 Extended unit matches 29 million templates in 4-to-many mode, thus the two units will satisfy the project requirements for response time.
3. The peak hour request quantity should satisfy project requirements. For example, the project expects that there may be up to 30,000 identification requests per hour. Single MegaMatcher Accelerator 3.0 Extended unit matches 29 million templates in 4-to-many mode, thus it will be able to process 10,440 requests per hour with the sample 10 million template database. Therefore, a cluster of 3 MegaMatcher Accelerator 3.0 Extended units will be required to process the required number of identification requests with the sample database.

Fault tolerance for a cluster of MegaMatcher Accelerators can be provided using these methods:

1. Spare MegaMatcher Accelerator units. A spare MegaMatcher Accelerator 3.0 unit "waits" until an operating unit fails and is used replace the failed one. Switching time from "wait" state to "operating" state depends on time required to copy database part used by failed node into spare node. If the failed node restored, it become the spare node.
2. Spare cluster. Two clusters of MegaMatcher Accelerator 3.0 units can be used to provide higher availability and failover. The clusters should have the same database loaded into each of them. One of the clusters can be used as "spare" and wait, until the "active" one fails and replace it. Switching time is very small even in case of manual switch, as the spare cluster already contains the database.
3. Two parallel clusters. This method also requires to run two clusters of MegaMatcher Accelerator 3.0 units with the same database loaded into each of them. Both clusters can run in parallel and provide 2 times higher performance. If one cluster fails, the other one will continue operation and provide the nominal performance.

Note, that "spare cluster" and "two parallel clusters" methods may require additional software and hardware for building high-availability clusters.

Back to top of this page

Contents of MegaMatcher Standard SDK and Extended SDK

MegaMatcher SDK is intended for development of large-scale AFIS or multi-biometric identification products. Fingerprint, face, iris and palm print recognition engines are included in MegaMatcher 4.0 SDK.

MegaMatcher 4.0 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 4.0 supports BioAPI 2.0. To ensure system compatibility with other software, WSQ component is available, as well as modules for conversion between MegaMatcher template and biometric standards.

MegaMatcher 4.0 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.

These types of MegaMatcher 4.0 SDK are available:

• MegaMatcher 4.0 Standard SDK for developing a client/server based multi-biometric fingerprint-face-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 or installation licenses can be additionally purchased for building high performance systems that match tens of millions fingerprints and/or irises per second.
• MegaMatcher 4.0 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 4.0 Standard SDK and ready-to-use cluster server software. This SDK also allows to develop network-based and web-based systems.

The table below compares MegaMatcher 4.0 Standard SDK and MegaMatcher 4.0 Extended SDK. Note that the table lists only those components that are included with the SDKs and make difference between the Standard and Extended SDKs; the other components (listed below the table) are not included with an SDK but can be purchased additionally.

Additional licenses for these components are available for MegaMatcher 4.0 SDK customers:

Fingerprint components: Fingerprint Extractor Fingerprint Segmenter Fingerprint BSS Fingerprint WSQ Fingerprint Client Fingerprint Matcher Fast Fingerprint Matcher	Face components: Face Extractor Face BSS Face Client Face Matcher Fast Face Matcher	Iris components: Iris Extractor Iris BSS Iris Client Iris Matcher Fast Iris Matcher
Palm print components: Palm Print Client Palm Print Matcher	Server and cluster components: Matching Server Cluster Server (available only for MegaMatcher 4.0 Extended SDK customers)

MegaMatcher 4.0 SDK includes programming samples and tutorials that show how to use the components of the SDK to perform fingerprint, face and iris template extraction or matching against other templates. The samples and tutorials are available for these programming languages and platforms:

Back to top of this page

Supported fingerprint scanners under Microsoft Windows

The table below explains which scanners are supported by MegaMatcher SDK, MegaMatcher On Card SDK and VeriFinger 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.

Back to top of this page

Supported Cameras and Webcams

These cameras are supported by MegaMatcher SDK, MegaMatcher On Card SDK and VeriLook SDK:

• Any webcam or camera that is accessible using:
  • DirectShow interface for Microsoft Windows platform.
  • Video4Linux interface for Linux platform.
  • QuickTime interface for Mac platform.
• Also these specific models of high-resolution cameras are supported:
  • Axis M1114 camera (Microsoft Windows only)
  • Cisco 4500 IP camera (Microsoft Windows and Linux)
  • IrisGuard IG-AD100 – face & iris camera (Microsoft Windows only)
  • Mobotix DualNight M12 IP camera (Microsoft Windows and Linux)
  • PiXORD N606 camera (Microsoft Windows and Linux)
  • Prosilica GigE Vision camera (Microsoft Windows and Linux)
  • VistaFA2 / VistaFA2E face & iris cameras (Microsoft Windows only)
  • VistaMT Multimodal Biometric Device (Microsoft Windows only)

Simultaneous capture from multiple cameras is possible.

A video file can be also used as a data source for applications based on VeriLook SDK or MegaMatcher SDK.

Back to top of this page

Supported eye iris scanners and platforms

The table below explains which iris scanners are supported by MegaMatcher 4.0 SDK and VEriEye 2.3 SDK under different versions of Microsoft Windows.

We are always looking for scanners' manufacturers to include the support for their eye iris scanners to our products. Please, contact us for more details.

Back to top of this page

MegaMatcher SDK System Requirements

System Requirements for applications based on MegaMatcher client-side components

• PC with x86 (32bit) or x86-64 (64bit) compatible processors or Mac with x86 or PowerPC compatible processors. 2 GHz processor or better is recommended, as template creation time directly depends on CPU speed.
  On one core of Intel Core 2 running at 2.66 GHz it takes:
  • 0.19 - 0.23 seconds for fingerprint template creation from an image captured with AFIS class single finger scanner;
  • 0.08 - 0.21 seconds for face template creation;
  • 0.13 - 0.17 seconds for iris template creation;
  • about 6.8 seconds for palm print template creation;
  • 0.1-0.2 seconds for WSQ compression/decompression.
• at least 128 MB of free RAM should be available for the application.
• Free space on hard disk drive (HDD):
  • at least 1 GB required for the development.
  • 100 MB for client-side components deployment.
  • Additional space optionally would be required in these cases:
    • MegaMatcher does not require the original biometric data (such as fingerprint image or photo) to be stored for the matching; it is enough to use the templates. However, we would recommend to store this data on hard drive for the potential future usage.
    • Usually a database engine runs on back-end servers (on separate computer). However, DB engine can be installed together with MegaMatcher client-side components and Matching Server on the same computer for standalone applications. In this case more HDD space for biometric templates storage must be available. For example, 1 million users templates (each with 2 fingerprint records) stored using a relational database would require about 2 GB of free HDD space.
• Optionally, depending on biometric modalities and requirements:
  • A fingerprint scanner. MegaMatcher SDK includes support modules for more than 70 models of fingerprint scanners under Microsoft Windows, Linux and Mac OS X platforms.
  • A webcam or camera (recommended frame size: 640 x 480 pixels) for face images capturing. MegaMatcher SDK includes support modules for several cameras. Any other webcam or camera should provide DirectShow interface for Windows platform, Video4Linux interface for Linux platform or QuickTime interface for Mac platform.
  • An iris camera (recommended image size: 640 x 480 pixels) for iris image capture. MegaMatcher SDK includes support modules for several iris cameras.
  • A palm print scanner.
  • A flatbed scanner for fingeprint or palm print data capturing from paper can be used. 500dpi or 1000dpi FBI certified scanners are recommended. Flatbed scanners are supported only under Microsoft Windows platform and should have TWAIN drivers.
• Network/LAN connection (TCP/IP) for communication with Matching Server, MegaMatcher Cluster Server or MegaMatcher Accelerator unit(s). MegaMatcher client-side components can be used without network if they are used only for data collection.
  Communication is not encrypted therefore, if communication must be secured, we would recommend to use a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools).
• Linux specific requirements:
  • Linux 2.6 or newer kernel, 32-bit or 64-bit. If a fingerprint scanner is required, it is recommended to choose 32-bit platform as most scanners have only 32-bit support.
  • glibc 2.3.6 or newer
  • GTK+ 2.10.x or newer libs and dev packages (to run SDK samples and applications based on them)
  • GCC-4.0.x or newer (for application development)
  • GNU Make 3.81 or newer (for application development)
  • Video4Linux (for face capture using camera/webcam)
• Microsoft Windows specific requirements:
  • Microsoft Windows 2000/XP/2003/2008/Vista/7, 32-bit or 64-bit. If a fingerprint scanner is required, it is recommended to choose 32-bit platform as most scanners have only 32-bit support.
  • Microsoft .NET framework 2.0 (for .NET components usage)
  • Microsoft Visual Studio 2005 SP1 or newer (for application development)
  • Microsoft DirectX 9.0 or later (for face capture using camera/webcam)
• Mac OS X specific requirements:
  • Mac OS X (version 10.4 or newer)
  • QuickTime (for camera/webcam usage)
  • XCode 2.4 or newer (for application development)

System Requirements for Matching Server and server-side matching components

• PC or server with x86 (32-bit) or x86-64 (64-bit) compatible CPU.
  • 64-bit platform must be used when large databases (more than 2.5 million fingerprints or more than 580,000 users with 2 fingerprints and 1 face enrolled) used and 3 GB RAM is not enough for templates storing in RAM.
  • Intel Core 2 2.66 GHz processor or better is recommended.
  • Computer with processors that have two or more cores can run more than one instance of MegaMatcher Cluster Node (see also licensing model). In this case the memory and disk requirements for the computer should be multiplied by the number of running nodes.
• Enough free RAM for Matching Server code (about 5 MB), matching engines and templates. 1 million users templates (each with 2 fingerprint records) require about 2 GB of RAM. At least 20% reserve recommended and some additional memory may be taken by an operating system. Therefore to hold mentioned 1 million users data, 3 GB of free RAM is recommended for the computer running MegaMatcher Cluster Node software.
• Free space on hard disk drive (HDD):
  • 5MB required for Matching Server software.
  • A database engine itself requires HDD space for running. Please refer to HDD space requirements from the database engine providers.
  • Enough HDD space to store templates and relation data. For example, 1 million users templates (each with 2 fingerprint records) stored using a relational database would require about 2.2 GB of free HDD space. The amount of relational data depends on configuration; for example, additional 10 MB is enough for storing 1 mln users gender data.
• Database engine or connection with it. Usually a DB engine required for Matching Server is runing on the same computer as Matching Server software. MegaMatcher SDK contains support modules for Microsoft SQL Server (only for Microsoft Windows platform), PostgreSQL, MySQL, Oracle, SQLite and memory DB. The fastest option is memory DB but it does not support relational queries, therefore the recommended option is SQLite, as it requires less resources than other options but provides enough functionality.
• Network/LAN connection (TCP/IP) for the communication with MegaMatcher Cluster Server or client-side applications. Communication is not encrypted therefore if communication must be secured, we would recommend to use a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools).
• Linux specific requirements:
  • Linux 2.6 or newer kernel, 32bit or 64bit.
  • glibc 2.3.6 or newer
• Microsoft Windows specific requirements:
  • Microsoft Windows 2000/XP/2003/2008/Vista/7, 32-bit or 64-bit.

System Requirements for MegaMatcher Cluster Server

• PC or server with x86 (32-bit) or x86-64 (64-bit) compatible CPU. 2 GHz processor or better is recommended. MegaMatcher Cluster Server distributes identification tasks over cluster nodes, performs cluster work monitoring, collects results and reports results to the client side. Computer speed for the MegaMacher Cluster Server speed is not critical but the computer must be as much stable as possible.
• Enough free RAM for MegaMatcher Cluster Server code (about 5 MB), ongoing tasks and results. For example, 1,000 matching tasks each with 2 fingerprint records would require about 3 MB of RAM.
• Free space on hard disk drive (HDD):
  • 5 MB required for MegaMatcher Cluster Server software.
  • Up to 2 MB required for saving server state.
  • If a database engine is installed on the same computer, enough HDD space for DB engine installation and data storage is required. For example, 1 million users templates (each with 2 fingerprint records) stored using a relational database would require about 2.2 GB of free HDD space.
• Database engine (optional). A connection to a database engine running on a different computer can be provided or the engine can be installed on the same computer with MegaMatcher Cluster Server. MegaMatcher SDK contains support modules for Microsoft SQL Server (only for Microsoft Windows platform), PostgreSQL, MySQL, Oracle and SQLite. SQLite is recommended only for development or evaluation purposes.
• Network/LAN connection (TCP/IP) for the communication with MegaMatcher Cluster Nodes and client side. Communication is not encrypted therefore if communication must be secured, we would recommend to use a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools).
• Linux specific requirements:
  • Linux 2.6 or newer kernel, 32bit or 64bit.
  • glibc 2.3.6 or newer
• Microsoft Windows specific requirements:
  • Microsoft Windows 2000/XP/2003/2008/Vista/7, 32bit or 64bit.

Supported Development Environments

These development environments are supported by MegaMatcher SDK:

• Microsoft Windows platform, Microsoft Visual Studio 2005 SP1 (or newer) is required
• Linux, following tools are required:
  • GCC-4.0.x or newer
  • GNU Make 3.81 or newer
  • pkg-config-0.21 or newer (optional; only for database engines support modules compilation)

Back to top of this page

Technical Specifications

All specifications are given for Intel Core2 processor with 4 cores running at 2.66 GHz

All biometric templates should be loaded into RAM before identification, thus the maximum biometric templates database size is limited by the amount of available RAM.

• Fingerprint scanners are recommended to have at least 500 dpi resolution and at least 1" x 1" fingerprint sensors
• Face capture cameras are recommended to produce at least 640 x 480 pixels images.
• Face recognition engine has certain tolerance to face posture:
  • head roll (tilt) – ±180 degrees (configurable);
    ±15 degrees recommended as it is the fastest setting which is usually sufficient for most near-frontal face images.
  • head pitch (nod) – ±15 degrees from frontal position.
  • head yaw (bobble) – ±15 degrees from frontal position.
• Iris capture cameras are recommended to produce at least 640 x 480 pixels images.

MegaMatcher biometric template matching algorithm can use more than one processor core on multi-core processors allowing to increase template matching speed. The template matching speeds in the table below are given as a range, where the smaller number means matching speed using 1 processor core, while the larger number means matching speed using all 4 processor cores.

Notes:
(1) Face template extraction time depends on the selected template size.
(2) MegaMatcher 4.0 allows to store multiple biometric records in a template; in this case the template size is the sum of all included biometric records.
(3) Here one template contains one biometric record (fingerprint, face or iris respectively).
(4) The speeds are given for one PC with Intel Core2 processor running at 2.66 GHz. If a cluster is used, the speeds should be multiplied by the number of cluster nodes.

See also: technical specifications for MegaMatcher Palm Print engine.

Back to top of this page

Reliability and Performance Test Results

All tests were performed on Intel Core2 processor with 4 cores running at 2.66 GHz.

The identification reliability and speed are important for large-scale systems. MegaMatcher SDK includes a fused algorithm for fast and reliable identification using several biometric templates taken from the same person. The tests with MegaMatcher biometric 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.
• 1 face record.
• 1 iris record.
• 2 fingerprint records taken from same person's different fingers.
• 2 iris records taken from same person's different eyes.
• 1 fingerprint + 1 face records taken from the same person.
• 1 face + 1 iris records taken from the same person.
• 1 fingerprint + 1 iris records taken from the same person.
• 1 fingerprint + 1 face + 1 iris records taken from the same person.

Two tests were performed with each template type:

• Test 1 maximized matching accuracy. MegaMatcher 4.0 fused algorithm reliability in this test is shown as blue curves on the ROC charts.
• Test 2 maximized matching speed. MegaMatcher 4.0 fused algorithm reliability in this test is shown as red curves on the ROC charts.

Template matching was performed using all 4 cores of the processor.

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).

The tests with templates that contained 1 fingerprint + 1 face + 1 iris records produced 0 % FRR for all FARs.

These tests show that a large-scale automated biometric identification system based on MegaMatcher provides high identification reliability when using fingerprints, using fused same-biometric (different fingerprints or irises from the same person) matching significantly reduces FRR, and using multi-biometric identification results in a significant reliability increase, allowing the system to reach almost 0 % FRR.

See also: reliability testing results for MegaMatcher Palm Print engine.

Back to top of this page

MINEX Certification

In 2007 MegaMatcher SDK fingerprint technology received full MINEX Certification. NIST certified MegaMatcher for use in personal identity verification program applications. MegaMatcher fingerprint technology is also used in VeriFinger SDK.

The Minutiae Interoperability Exchange Test (MINEX) evaluates fingerprint template encoding and matching to determine compliance with the government's Personal Identity Verification (PIV) program for the identification and authentication of Federal employees and contractors. The MINEX program provides measurements of fingerprint algorithm performance and interoperability to both government and commercial entities.

MegaMatcher is one of only 12 algorithms worldwide to receive full MINEX certification for both fingerprint template encoding and matching. This certification puts MegaMatcher SDK into the U.S. government buyers' certified list of fingerprint recognition algorithms.

See Neurotechnology press release about this subject.

Back to top of this page