|
Biometrics
Robotics
Resources
Ordering


Services
|
MegaMatcher SDK System Requirements
System requirements for:
System requirements for MegaMatcher client-side components
-
PC or Mac with x86 (32-bit) or x86-64 (64-bit) 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 Q9400 running at 2.67 GHz it takes:
- 0.20 - 0.25 seconds for fingerprint template creation from an image captured with AFIS class single finger scanner;
- 0.07 - 0.19 seconds for face template creation;
- 0.10 - 0.12 seconds for iris template creation;
- 0.12 - 0.15 seconds for voice 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 80 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, GStreamer 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 microphone.
Any microphone that is supported by the operating system can be used.
-
A palm print scanner.
-
A flatbed scanner for fingerprint 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.
-
Integrators can also write plug-ins to support their biometric capture devices using the plug-in framework provided with the Device Manager from the MegaMatcher SDK.
-
Network/LAN connection (TCP/IP) for communication with Matching Server, 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, note that a number of scanners are supported only on 32-bit OS.
- glibc 2.7 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)
- GStreamer 0.10.23 (with gst-plugin-base and gst-plugin-good) or newer (for face and voice capture using camera/webcam and/or microphone)
- libasound 1.0.x or newer (for voice capture)
- udev-143 or newer with libudev (for camera and microphone usage)
- pkg-config-0.21 or newer (optional; only for database engines support modules compilation)
-
Microsoft Windows specific requirements:
-
Microsoft Windows XP / Vista / 7, 32-bit or 64-bit.
If a fingerprint scanner is required, note that a number of scanners are supported only on 32-bit OS.
- 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
-
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 matching components (see also licensing model).
In this case the memory and disk requirements for the computer should be multiplied by the number of running matching components.
-
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 Matching Server 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 the Matching Server is running on the same computer.
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 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, 32-bit or 64-bit.
- glibc 2.7 or newer
-
Microsoft Windows specific requirements:
- Microsoft Windows XP / Vista / 7 / Server 2003 / Server 2008, 32-bit or 64-bit.
System requirements for MegaMatcher cluster nodes
Similar or even exactly the same hardware configuration is recommended for all cluster node machines, as even one slow node will affect the performance of the whole cluster.
-
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 matching components (see also licensing model).
In this case the memory and disk requirements for the computer should be multiplied by the number of running matching components.
-
Enough free RAM for cluster node 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 cluster node software.
-
Free space on hard disk drive (HDD):
- 5MB required for cluster node 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 the cluster node is running on the same computer.
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 Cluster Server.
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.
- glibc 2.7 or newer
-
Microsoft Windows specific requirements:
- Microsoft Windows XP / Vista / 7 / Server 2003 / Server 2008, 32-bit or 64-bit.
System requirements for Cluster Server
-
PC or server with x86 (32-bit) or x86-64 (64-bit) compatible CPU.
2 GHz processor or better is recommended.
The 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 Cluster Server is not critical but the computer must be as much stable as possible.
-
Enough free RAM for 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 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 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 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, 32-bit or 64-bit.
- glibc 2.7 or newer
-
Microsoft Windows specific requirements:
- Microsoft Windows XP / Vista / 7 / Server 2003 / Server 2008, 32-bit or 64-bit.
Go to MegaMatcher contents
|
Products
AFIS or multi-biometric fingerprint, iris, face and voice identification for large-scale systems.
Face identification for PC or Web solutions.
Fingerprint identification for PC and Web solutions.
Iris identification for PC and Web solutions.
Speaker recognition for PC or Web applications.
Object recognition for robotics and computer vision.
More products for developers:
End-user products:
- NCheck Finger Attendance – an attendance control application that uses fingerprint biometrics to perform employee identification.
- NVeiler Video Filter – a plug-in for VirtualDub that automatically detects faces in a frame, tracks the faces (or other objects) in subsequent frames and hides them.
|