MegaMatcher Accelerator

Solution for large-scale AFIS or multi-biometric systems

MegaMatcher Accelerator is a hardware/software solution that provides high speed, high volume biometric identification for national-scale projects.

The Extreme and Extended versions are designed to run on server hardware and perform fast biometric template matching on the server-side of a large-scale AFIS or multi-modal system. The Standard version and Development Edition are intended to be run on a common PC. MegaMatcher Accelerator software licenses are available for new and existing MegaMatcher Extended SDK customers.

View Data Sheet Watch a Demo
Features and Capabilities
Proven in national-scale projects, including voter registration and national ID.
NIST MINEX-compliantfingerprint engine, NIST IREX proven iris engine.
Available as a ready-to-use biometric solution with server hardware or as biometric software that will run on server hardware or a common PC.
Up to 1,200,000,000 fingerprints, faces or irises per second matching speed on a single unit.
Fingerprint, iris, face and palmprint modalities supported.
Scalable cluster architecture.
Support for ISO & ANSI fingerprint template standards.
Suitable for duplicates search.

Megamatcher Accelerator Editions

MegaMatcher Accelerator is available in these editions:

MegaMatcher Accelerator Extreme is designed to run on server hardware with dual Xeon processors and 512 GB of RAM. Optionally, a ready-to-use solution with server hardware and pre-installed MegaMatcher Accelerator software can be provided.
MegaMatcher Accelerator Extended is designed to run on server hardware with dual Xeon processors and 128 GB of RAM. Optionally, a ready-to-use solution with server hardware and pre-installed MegaMatcher Accelerator software can be provided.
MegaMatcher Accelerator Standard is designed to run on a PC with Core i7 processor and 16 GB of RAM
MegaMatcher Accelerator Development Edition software is designed to run on a PC with Core i7 processor and 16 GB of RAM. This version is available with the MegaMatcher 12.1 Extended SDK

MegaMatcher Accelerator software provides these capabilities for biometric identification:

Fast matching. A single MegaMatcher Accelerator 12.1 Extreme unit can match up to 1.2 billion fingerprints per second or up to 1.2 billion irises per second or up to 1.2 billion faces per second in 1-to-many mode using the Neurotechnology proprietary biometric template format. A single MegaMatcher Accelerator 12.1 Extended unit can match up to 100 million fingerprints per second or up to 200 million irises per second or up to 100 million faces per second or up to 2 million palmprints per second in 1-to-many mode. A PC with MegaMatcher Accelerator 12.1 Standard software can match up to 35 million fingerprints per second or up to 70 million irises per second or up to 35 million faces per second in 1-to-many mode.
Matching accuracy. MegaMatcher Accelerator matching engines are based on biometric identfication algorithms which had been recognized by NIST and other authoritative institutions as the most reliably accurates even at the highest matching speeds.
Multiple modalities support. MegaMatcher Accelerator 12.1 can be used within a biometric system that contains templates with any number of fingerprint, iris, face and/or palmprint records.
Full database search. The biometric engines included in MegaMatcher Accelerator do not perform internal database indexing or pre-classification (by fingerprint type, eye color etc) thus avoiding false rejections when incorrect classifiers appear. This way the whole database is scanned comprehensively during every matching request and very low false rejection ensured. On the other hand, integrators may use non-biometric classifiers like gender or a country's region to optimize system size.
Optimal system size. A system based on the MegaMatcher Accelerator 12.1 solution can be configured to perform fast candidate selection using irises and/or faces and/or several fingerprints, and then use other biometric modalities to validate selection results. This approach allows the system to reach optimal matching speed and reliability while keeping the overall system cost within the defined limits.
ISO & ANSI standards support. MegaMatcher Accelerator allows the use of ANSI and ISO biometric standards for fingerprint templates.
Scalable architecture. Multiple MegaMatcher Accelerator units can be combined together in a cluster for higher matching speed. For example, a cluster of 4 MegaMatcher Accelerator 12.1 Extended units would enable matching at a rate of about 108 million templates per second (when a template contains 4 fingerprint records), a cluster of 10 units – about 270 million templates per second, and so on. No additional cluster software is required, as MegaMatcher Accelerator includes all the necessary software which is easily managed through a web interface
Suitable for duplicates search. Searching for duplicates in a biometric template database is a task that requires many computations, as each biometric template needs to be verified with every other template in the database. MegaMatcher Accelerator provides enough speed to complete duplicate searching in a reasonable time. Scalable architecture allows the combination of several MegaMatcher Accelerator units for tasks involving larger databases.
Technology Awards

MegaMatcher Accelerator technology is based on awards-winning fingerprint and iris recognition algorithms.

MINEX Evaluations by NIST

MINEX III evaluation was successfully passed in 2015. In 2019 Neurotechnology's fingerprint template generator algorithm has been ranked the first in the NIST MINEX interoperability category; the fingerprint matching algorithm has also been ranked as the front-runner in terms of interoperability and, when combined, the two have become the supreme accuracy, high speed fingerprint recognition system.
MINEX Ongoing evaluation was successfully passed in 2014. The second place in the Ongoing MINEX ranking for fingerprint matching algorithms was achieved. MegaMatcher technology was recognized by the NIST as fully MINEX compliant.

FVC-OnGoing Results

In 2020 MegaMatcher fingerprint recognition algorithm has shown the top result at the FVC-onGoing evaluation. The fingerprint extractor and matcher were ranked as the most accurate for both FV-STD-1.0 and FV-HARD-1.0 benchmarks.
In 2019 MegaMatcher palm print matching algorithm has shown the top result at the FVC-onGoing evaluation. The algorithm was the most accurate overall and fastest among the five most accurate matchers.

PFT II AND PFT III (PROPRIETARY FINGERPRINT TEMPLATE) EVALUATIONS

Different versions of Neurotechnology's fingerprint recognition algorithm were submitted to the NIST Proprietary Fingerprint Template Evaluation. The algorithm's template matching accuracy was among the best participants at the previous PFT II evaluation. Our latest submissions to the PFT II and the ongoing PFT III are in average the most accurate algorithms in all the experiments.

FpVTE (Fingerprint Vendor Technology Evaluations) by NIST

FpVTE 2012 – in 2015 NIST recognized Neurotechnology's fingerprint identification algorithm as one of the fastest and most accurate among the evaluation's participants.
FpVTE 2003 – one of the best reliability results in the Middle Scale Test were shown. Neurotechnology participated in FpVTE 2003 under the name Neurotechnologija.

IREX evaluations by NIST

IREX 10 – in 2020 Neurotechnology's iris recognition algorithm has been judged by NIST as the second most accurate among the IREX 10 participants. The submitted algorithm featured much faster template creation and search time, and much smaller template size than the only more accurate contender.
IREX IX – in 2018 Neurotechnology's iris recognition algorithm has been judged by the NIST as the second most accurate among the participants. The accelerated version of the algorithm was nearly 50 times faster than any other matcher in the NIST IREX IX evaluation.
IREX IV – in 2013 Neurotechnology's iris recognition algorithm has been judged the by the NIST as one of the fastest and most accurate among the participants.
IREX III – in 2012 MegaMatcher iris matching algorithm was the second fastest and provided 3 times higher recognition accuracy than the only faster contender.
Technical Specifications
Database storage capacities for a single MegaMatcher Accelerator 12.1 unit are:
  • 160,000,000 fingerprint records or 200,000,000 iris records or 40,000,000 face records for each MegaMatcher Accelerator 12.1 Extreme unit.
  • 40,000,000 fingerprint records or 50,000,000 iris records or 10,000,000 face records or 4,000,000 palmprint records for each MegaMatcher Accelerator 12.1 Extended unit.
  • 4,000,000 fingerprint records or 5,000,000 iris records or 1,000,000 face records or 400,000 palmprint records for each PC that runs MegaMatcher Accelerator 12.1 Standard or Development Edition software.

Note, that the palmprint engine is not available with MegaMatcher Accelerator 12.1 Extreme.

If a biometric template contains several fingerprint, palmprint, face and/or iris records, the database storage capacity changes proportionally. The table below shows storage capacities for some common combinations of fingerprints, palmprints, faces and/or irises records. There are no limitations on the quantity of fingerprint, palmprint, face or iris records in a template.

Database storage capacities for single MegaMatcher Accelerator unit (templates)
One template contains: MegaMatcher
Accelerator 12.1
Extreme		 MegaMatcher
Accelerator 12.1
Extended		 MegaMatcher
Accelerator 12.1
Standard		 MegaMatcher
Accelerator 12.1
Development Edition
1 fingerprint record 160,000,000 40,000,000 4,000,000 4,000,000
2 fingerprint records 80,000,000 20,000,000 2,000,000 2,000,000
1 face record 40,000,000 10,000,000 1,000,000 1,000,000
1 iris record 200,000,000 50,000,000 5,000,000 5,000,000
2 iris records 100,000,000 25,000,000 2,500,000 2,500,000
1 palmprint record Not supported 4,000,000 400,000 400,000
2 palmprint records Not supported 2,000,000 200,000 200,000
1 fingerprint + 1 face records 40,000,000 10,000,000 1,000,000 1,000,000
2 fingerprint + 1 face records 40,000,000 10,000,000 1,000,000 1,000,000
4 fingerprint + 1 face records 40,000,000 10,000,000 1,000,000 1,000,000
10 fingerprint + 1 face records 16,000,000 4,000,000 400,000 400,000
1 fingerprint + 1 iris records 160,000,000 40,000,000 4,000,000 4,000,000
1 fingerprint + 2 iris records 100,000,000 25,000,000 2,500,000 2,500,000
2 fingerprint + 1 iris records 80,000,000 20,000,000 2,000,000 2,000,000
2 fingerprint + 2 iris records 80,000,000 20,000,000 2,000,000 2,000,000
4 fingerprint + 2 iris records 40,000,000 10,000,000 1,000,000 1,000,000
10 fingerprint + 2 iris records 16,000,000 4,000,000 400,000 400,000
4 fingers + 1 palm record Not supported 4,000,000 400,000 400,000
10 fingers + 2 palms records Not supported 2,000,000 200,000 200,000
1 face + 1 iris records 40,000,000 10,000,000 1,000,000 1,000,000
1 face + 2 iris records 40,000,000 10,000,000 1,000,000 1,000,000
1 face + 1 palm record Not supported 4,000,000 400,000 400,000
1 face + 2 palms records Not supported 2,000,000 200,000 200,000
4 fingers + 1 face + 2 iris records 40,000,000 10,000,000 1,000,000 1,000,000
10 fingers + 1 face + 2 iris records 16,000,000 4,000,000 400,000 400,000

The tables below show the performance of MegaMatcher Accelerator fast fingerprint, face and iris matching engines on the specified hardware. The fingerprint engine specifications are valid for databases that contain flat fingerprint templates with 48 minutiae in average.

MegaMatcher Accelerator 12.1 Extreme biometric engines matching speed
One template contains: Speed (templates per second)
1 fingerprint record 1,200,000,000
2 fingerprint records 600,000,000
4 fingerprint records 300,000,000
8 fingerprint records 150,000,000
10 fingerprint records 120,000,000
1 face record 1,200,000,000
1 iris record 1,200,000,000
2 iris records 600,000,000

MegaMatcher Accelerator 12.1 Extended biometric engines matching speed
(templates per second)
One template contains: Maximized
matching speed
configuration		 Default settings configuration Maximized
matching accuracy
configuration
1 fingerprint record 100,000,000 84,000,000 15,000,000
2 fingerprint records 55,000,000 42,000,000 6,000,000
4 fingerprint records 27,000,000 21,000,000 2,600,000
8 fingerprint records 13,000,000 11,000,000 1,600,000
10 fingerprint records 10,500,000 9,000,000 1,500,000
1 face record 100,000,000
1 iris record 200,000,000
2 iris records 100,000,000
1 palmprint record 2,000,000
2 palmprint records 1,000,000

MegaMatcher Accelerator 12.1 Standard biometric engines matching speed
(templates per second)
One template contains: Maximized
matching speed
configuration		 Default settings configuration Maximized
matching accuracy
configuration
1 fingerprint record 35,000,000 27,000,000 3,500,000
2 fingerprint records 18,000,000 13,000,000 1,600,000
4 fingerprint records 8,000,000 6,000,000 700,000
8 fingerprint records 4,000,000 3,000,000 400,000
10 fingerprint records 3,500,000 2,500,000 350,000
1 face record 35,000,000
1 iris record 70,000,000
2 iris records 35,000,000
1 palmprint record 600,000
2 palmprint records 300,000

MegaMatcher Accelerator 12.1 Development Edition biometric engines matching speed
(templates per second)
One template contains: Maximized
matching speed
configuration		 Default settings configuration Maximized
matching accuracy
configuration
1 fingerprint record 1,000,000 1,000,000 1,000,000
2 fingerprint records 500,000 500,000 500,000
4 fingerprint records 250,000 250,000 250,000
8 fingerprint records 125,000 125,000 125,000
10 fingerprint records 100,000 100,000 100,000
1 face record 1,000,000
1 iris record 1,000,000
2 iris records 500,000
1 palmprint record 20,000
2 palmprint records 10,000
System Requirements
MegaMatcher Accelerator software is distributed as Docker containers.
  • Any modern Linux distribution can be used as a base operating system, including Debian, Ubuntu or CentOS.
  • The distribution package includes scripts for automatic installation of all necessary components.
MegaMatcher Accelerator 12 Extreme software should be run on server hardware or virtual machine with these specifications:
  • 24 processor cores, running at 2.6 GHz or higher frequency.
    • Two Intel Xeon Gold 6126 processors can be used as an example.
  • RAM, depending on the number of the biometric engines:
    • 512 GB RAM – for single biometric engine or two biometric engines;
    • 1024 GB RAM – for three biometric engines.
  • Persistent storage:
    • SSD is recommended for increasing overall system performance.
  • High-speed network connection
MegaMatcher Accelerator 12.1 Extended software should be run on server hardware or virtual machine with these specifications:
  • 24 processor cores, running at 2.6 GHz or higher frequency.
    • Two Intel Xeon Gold 6126 processors can be used as an example.
  • RAM, depending on the number of the biometric engines:
    • 128 GB RAM – for single biometric engine;
    • 256 GB RAM – for two biometric engines;
    • 384 GB RAM – for three biometric engines;
    • 512 GB RAM – for four biometric engines.
  • Persistent storage:
    • SSD is recommended for increasing overall system performance.
  • High-speed network connection
MegaMatcher Accelerator 12.1 Standard or Development Edition software should be run on PC, server hardware or virtual machine with these specifications:
  • 4 processor cores, running at 3.5 GHz or higher frequency.
  • 16 GB of RAM
  • Persistent storage:
    • SSD is recommended for increasing overall system performance;
  • High-speed network connection
MegaMatcher Accelerator Extreme

MegaMatcher Accelerator 12.1 Extreme is a family of biometric solutions for fast fingerprint, iris and face matching on the server-side of an AFIS or multi-biometric system. The solutions are intended for national-scale biometric identification projects with hundreds of millions of people enrolled in the database.

These biometric matching engines can be used with MegaMatcher Accelerator 12.1 Extreme:
  • Fast fingerprint, iris and face matching engines that can be used separately or together. See technical specifications for engine comparison and licensing model for engine availability.
  • Fingerprint, face, iris and voiceprint matching engines that can be used separately or together to validate matching results produced by the fast fingerprint, face and/or iris engines. See MegaMatcher SDK reliability tests for more information.
MegaMatcher Accelerator software is distributed as Docker containers for using on Linux OS.
Server hardware is optionally available. In this case the MegaMatcher Accelerator 12.1 Extreme software will be pre-installed by Neurotechnology on each unit, and the customers will receive ready-to use hardware/software solution.
HPE ProLiant DL360 Gen10 server units are offered with these specifications:
  • 2 x Intel Xeon Gold 6126 processor (12 cores, 19.25M cache, 2.6 GHz);
  • RAM, depending on the number of biometric engines:
    • 512 GB RAM – for single biometric engine or two biometric engines;
    • 1024 GB RAM – for three biometric engines;
  • Persistent storage:
    • 2x HPE 400GB SATA 6G Write Intensive (2.5") SC SSD or HDD with similar capacity;
  • HPE iLO Advanced;
  • HPE Smart Array P408i-a SR Gen10 (8 Internal Lanes_2GB Cache) 12G.
Multiple MegaMatcher Accelerator 12.1 Extreme units can be combined using the included cluster software to reach a higher level of performance.

A client communication module is included with MegaMatcher 12.1 Extended SDK. The module allows the sending of a task to MegaMatcher Accelerator, querying the status of the task, retrieving the results and then removing the task. A high-level API is provided for the developer, all low-level communications are hidden.

MegaMatcher Accelerator Extended

MegaMatcher Accelerator 12.1 Extended is a family of biometric solutions for fast fingerprint, palmprint, iris and face matching on the server-side of an AFIS or multi-biometric system. The solutions are intended for national-scale biometric identification projects with millions of people enrolled in the database.

These biometric matching engines can be used with MegaMatcher Accelerator 12.1 Extended:
  • Fast fingerprint, iris and face matching engines that can be used separately or together. See technical specifications or engine comparison and licensing model for engine availability.
  • Fingerprint, face, iris and voiceprint matching engines that can be used separately or together to validate matching results produced by the fast fingerprint, face and/or iris engines. See MegaMatcher SDK reliability tests for more information.
MegaMatcher Accelerator software is distributed as Docker containers for using on Linux OS.
Server hardware is optionally available. In this case the MegaMatcher Accelerator 12.1 Extreme software will be pre-installed by Neurotechnology on each unit, and the customers will receive ready-to use hardware/software solution.
HPE ProLiant DL360 Gen10 server units are offered with these specifications:
  • 2 x Intel Xeon Gold 6126 processor (12 cores, 19.25M cache, 2.6 GHz);
  • RAM, depending on the number of biometric engines:
    • 128 GB RAM (8 x 16 GB Dual Rank x8 DDR4-2666) – for single biometric engine;
    • 256 GB RAM (16 x 16 GB Dual Rank x8 DDR4-2666) – for two biometric engines;
    • 384 GB RAM (24 x 16 GB Dual Rank x8 DDR4-2666) – for three biometric engines;
    • 512 GB RAM (16 x 32 GB Dual Rank x8 DDR4-2666) – for four biometric engines.
  • Persistent storage:
    • 6 x 300 GB HDD (SAS, 12G Enterprise 10K SFF) is offered as a standard option;
    • SSD is recommended for increasing overall system performance.
  • HPE iLO Advanced;
  • HPE Smart Array P408i-a SR Gen10 (8 Internal Lanes_2GB Cache) 12G.
Multiple MegaMatcher Accelerator 12.1 Extreme units can be combined using the included cluster software to reach a higher level of performance.

A client communication module is included with MegaMatcher 12.1 Extended SDK. The module allows the sending of a task to MegaMatcher Accelerator, querying the status of the task, retrieving the results and then removing the task. A high-level API is provided for the developer, all low-level communications are hidden.

MegaMatcher Accelerator Standard

MegaMatcher Accelerator 12.1 Standard is a family of ready-to-use software products for fast fingerprint, palmprint, iris and face matching on the server-side of an AFIS or multi-biometric system. These products are intended for large-scale biometric projects with up to several million people enrolled in the database.

These biometric matching engines can be used with MegaMatcher Accelerator 12.1 Extended:
  • Fast fingerprint, iris and face matching engines that can be used separately or together. See technical specifications for engine comparison and licensing model for engine availability.
  • Fingerprint, face, iris and voiceprint matching engines that can be used separately or together to validate matching results produced by the fast fingerprint, face and/or iris engines. See MegaMatcher SDK reliability tests for more information.
MegaMatcher Accelerator software is distributed as Docker containers for using on Linux OS.
Server hardware is optionally available. In this case the MegaMatcher Accelerator 12.1 Extreme software will be pre-installed by Neurotechnology on each unit, and the customers will receive ready-to use hardware/software solution.
HPE ProLiant DL360 Gen10 server units are offered with these specifications:
Hardware is not included.
Several PCs with the Standard Accelerator software can be combined using the included cluster software to reach a higher level of performance.

A client communication module is included with MegaMatcher 12.1 Extended SDK. The module allows the sending of a task to MegaMatcher Accelerator, querying the status of the task, retrieving the results and then removing the task. A high-level API is provided for the developer, all low-level communications are hidden.

MegaMatcher Accelerator Development Edition

MegaMatcher Accelerator 12.1 Development Edition software is intended for developers who need to run MegaMatcher Accelerator software in-house for software development and support without the need to purchase a dedicated Standard or Extended unit. It is also suitable for for deploying pilot projects, as well as biometric projects with up to several million people enrolled in the database.

Provides the same API for the developers as the Standard, Extended and Extreme versions of MegaMatcher Accelerator, thus the system deployment only requires to replace it with MegaMatcher Accelerator 12.1 Standard, Extended or Extreme.
Has the same database capacity as the MegaMatcher Accelerator 12.1 Standard, but lower matching speed.
Fast fingerprint, palmprint, iris and face matching engines can be used separately or together.
One free license is available with the MegaMatcher 12.1 Extended SDK.
MegaMatcher Accelerator software is distributed as Docker containers for using on a PC with Linux OS (see system requirements).
Hardware is not included.

A client communication module is included with MegaMatcher 12.1 Extended SDK. The module allows the sending of a task to MegaMatcher Accelerator, querying the status of the task, retrieving the results and then removing the task. A high-level API is provided for the developer, all low-level communications are hidden.

Scalable High Productivity Systems

Large-scale biometric projects may have specific system performance requirements. The MegaMatcher Accelerator family of products is intended for large-scale AFIS / ABIS projects and offers different matching engines and editions for high performance during large number of requests.

MegaMatcher Accelerator provides easy system scalability and allows to start a biometric system from a single unit at the beginning, with further scaling up together with project capacity and speed requirements by expanding the system into cluster and/or upgrading the units using engines with higher capabilities.

MegaMatcher Accelerator is designed for using together with other components of MegaMatcher SDK, which provide biometric data capture and template extraction. These system architectures are usually used for specific projects

Template creation on client-side and matching on server-side- recommended for AFIS, border control, various ID issuing systems, such as passports, ID cards, voter registration.
Template creation and matching on server side recommended for online banking, government e-services and other mass scale systems, in which requests can be submitted by any device or computer.
Deduplication after all users data collected - recommended for ID issuing systems, which have previously collected biometric data, such as voter or population registry cleaning.

A combination of the mentioned architectures and components can be also used within a large-scale biometric system to reach optimal performance and/or availability.

MegaMatcher Accelerator software licenses are available for new and existing MegaMatcher Extended SDK customers.

MegaMatcher Automated Biometric Identification System, an integrated multi-biometric solution for national-scale identification projects, can be also considered. The solution can be customized by Neurotechnology for specific project needs

Template Creation on Client-Side and Matching on Server-Side

This is the most often used architecture for AFIS / ABIS, border control, various ID issuing systems, such as passports, ID cards or voter registration. It is suitable for various systems, ranging from small LAN-based systems to national-scale projects. The chart below shows the key components need for this architecture.

The ready-to-use MegaMatcher Accelerator 12.1 units are deployed on the server-side and include biometric engines for matching fingerprint, palmprint, face and iris templates, which can be easily scaled up at any time for higher performance based on the project requirements.

MegaMatcher template extraction components are used by integrators to develop client-side desktop or mobile applications. The components include all necessary functionality and performance for biometric data capture and template extraction for sending them to the server-side. The applications deployment needs only additional licenses for the corresponding components for each computer or device running the application.

Template Creation and Matching on Server-Side

This architecture is designed to be used for biometric systems, which need to process requests from a very large number of clients in scenarios like online banking or government e-services, as well as other mass scale systems with very large number of users. The chart below shows the key components needed for this architecture.

The ready-to-use MegaMatcher Accelerator 12.1 units are deployed on the server-side and include biometric engines for matching fingerprint, palmprint, face and iris templates, which can be easily scaled up at any time for higher performance based on the project requirements

MegaMatcher template extraction components are deployed on the server-side of the biometric system. The integrators need to develop application logic, which will operate with the template extraction components.

MegaMatcher biometric data capture components provide necessary functionality for client-side applications, which acquire biometric images from scanners or cameras and send them to the server-side for further template extraction. Applications deployment needs only additional licenses for the corresponding components for each computer or device running the application. Integrators can also implement image capture by themselves and send images to the server-side part of the system. In this case client-side applications deployment does not need any licenses for Neurotechnology components.

Deduplication After All Users Data Collected

This architecture is intended for large-scale projects, like voter registration or population registry cleaning, when users' biometric data collection is done in two steps. First, the biometric data is captured on multiple sites, which are not connected to the central database. Later, the biometric data from all sites is submitted to the central database and checked for duplicates. The chart below shows the key components need for this architecture

The ready-to-use MegaMatcher Accelerator 12.1 units are deployed on the server-side and include biometric engines for matching fingerprint, palmprint, face and iris templates, which can be easily scaled up at any time for higher performance based on the project requirements. Integrators will need to develop simple application logic for sending the biometric templates for for many-to-many deduplication and generating the duplicates search report. Note, that database deduplication task requires a lot of computational resources, as it needs to compare every biometric template with every other biometric template in a database.

MegaMatcher template extraction components may need to be deployed on the server-side, as usually the biometric data is captured as fingerprint, palmprint, face or iris images, which need to be processed into biometric templates. The integrators need to develop application logic, which will operate with the template extraction components.

MegaMatcher template extraction components may need to be deployed on the server-side, as usually the biometric data is captured as fingerprint, palmprint, face or iris images, which need to be processed into biometric templates. The integrators need to develop application logic, which will operate with the template extraction components.

You may also consider the MegaMatcher ABIS Cloud Service, which provides results for a reasonable price without the need to develop a solution.

Scalable Server-Side Matching With Megamatcher Accelerator

MegaMatcher Accelerator 12.1 is a solution for large-scale AFIS and multi-biometric projects, which is available as Development Edition, Standard, Extended and Extreme versions. A system based on MegaMatcher Accelerator with a single unit can be scaled up by adding more units to create a cluster and/or upgrading to a more powerful version of MegaMatcher Accelerator. The MegaMatcher Accelerator includes necessary software to enable system scalability, high availability and fault tolerance.

MegaMatcher Accelerator 12.1 software is provided with MegaMatcher 12.1 Extended SDK.

The table below compares different versions of MegaMatcher Accelerator 12.1 solution

Template matching components performance and scalabilty
Database capacity Matching speed
Cluster of MegaMatcher Accelerator 12.1 Development Edition with N units
Fingerprints N × 4,000,000

fingerprints

 N × 1,000,000

fingerprints per second
Faces N × 1,000,000

faces

 N × 1,000,000

faces per second
Irises N × 5,000,000

irises

 N × 1,000,000

irises per second
Palmprints N × 400,000

palmprints

 N × 20,000

palmprints per second
Cluster of MegaMatcher Accelerator 12.1 Standard with N units
Fingerprints N × 4,000,000

fingerprints

 N × 35,000,000

fingerprints per second
Faces N × 1,000,000

faces

 N × 35,000,000

faces per second
Irises N × 5,000,000

irises

 N × 70,000,000

irises per second
Palmprints N × 400,000

palmprints

 N × 600,000

palmprints per second
Cluster of MegaMatcher Accelerator 12.1 Extended with N units
Fingerprints N × 40,000,000

fingerprints

 N × 100,000,000

fingerprints per second
Faces N × 10,000,000

faces

 N × 100,000,000

faces per second
Irises N × 50,000,000

irises

 N × 200,000,000

irises per second
Palmprints N × 4,000,000

palmprints

 N × 2,000,000

palmprints per second
Cluster of MegaMatcher Accelerator 12.1 Extreme with N units
Fingerprints N × 160,000,000

fingerprints

 N × 1,200,000,000

fingerprints per second
Faces N × 40,000,000

faces

 N × 1,200,000,000

faces per second
Irises N × 200,000,000

irises

 N × 1,200,000,000

irises per second
Palmprints

Palmprint engine is not available
in MegaMatcher Accelerator Extreme Edition

Recommendations:

MegaMatcher Accelerator Development Edition has no limitations on cluster size, but in general it makes no sense to run more than 3 nodes in the cluster, as the whole system will cost like one MegaMatcher Accelerator Standard unit while providing lower performance.
MegaMatcher Accelerator Standard has no limitations on cluster size, but in general it makes no sense to run more than 2 nodes in the cluster, as the whole system will cost like one MegaMatcher Accelerator Extended unit while providing lower performance and capacity.
MegaMatcher Accelerator Extended has no limitations on cluster size, but in general it makes no sense to run more than 4 nodes in the cluster, as the whole system will cost like one MegaMatcher Accelerator Extreme unit while providing lower performance and capacity.
The matching speeds are provided for single-biometrics engines. If a template in a database contains multi-biometric entries, like fingerprint and face records belonging to the same person, the matching components will match proportionally lower number of persons' biometric database entries per second.
MegaMatcher Accelerator unit(s) can be used for fast candidate selection using irises, faces or several fingerprints with further results validation using slower fingerprint, face, iris and voiceprint matching engines which are also included with MegaMatcher Accelerator.
Smaller systems, which need to match up to 200,000 fingerprints, faces or irises per second, can be based on the Matching Server which is available in the MegaMatcher SDK.

Also, two or more MegaMatcher Accelerator based clusters can be connected together for a high availability system.

Megamatcher Accelerator Cluster Software

MegaMatcher Accelerator includes cluster software, thus multiple MegaMatcher Accelerator 12.1 units (cluster nodes) can be connected via network to a cluster. A cluster of MegaMatcher Accelerators may be scaled up at anytime, meeting changing project requirements such as an increase in number of users or request environment. The cluster software provides these advanced capabilities:

Horizontal scalability – achieved by adding new MegaMatcher Accelerator nodes to a cluster. Because each unit operates on a portion of the database, an increase in the number of MegaMatcher Accelerator units results in faster matching and a higher number of processed requests.

For example, there is a database with the biometric data for 15 million people (4 fingerprints for each user, 60 million fingerprints in total). The number of required MegaMatcher Accelerator units would be calculated in this way:

  • The whole database should fit into the memory of the MegaMatcher Accelerator units. A single MegaMatcher Accelerator 12.1 Extended unit stores 40 million fingerprints, therefore, 2 units would be required to store the 60 million fingerprint database.;
  • The response time for an identification request should satisfy project requirements. A single MegaMatcher Accelerator 12.1 Extended unit matches 27 million fingerprint templates per second in 4-to-many mode If the project requires receiving an an answer to an identification request in 1 second, therefore, two units will satisfy the project requirements for response time.
  • The peak hour request quantity should satisfy project requirements. For example, the project expects that there may be up to 15,000 identification requests per hour. A single MegaMatcher Accelerator 12.1 Extended unit matches 27 million fingerprint templates per second in 4-to-many mode, it will therefore be able to process 6,480 requests per hour with the sample 15 million template database. A cluster of 3 MegaMatcher Accelerator 12.1 Extended units will be required to process the expected number of identification requests in this case.
Vertical scalability – usually achieved by upgrading to a more powerful edition of MegaMatcher Accelerator. For example, a single MegaMatcher Accelerator Extended unit provides almost three times faster biometric matching and can store ten times more biometric templates compared to a single MegaMatcher Accelerator Standard unit.
Fault tolerance – a cluster of MegaMatcher Accelerators can restore its operation after one or more of the nodes abnormally leaves the cluster for any reason, like hardware or network failure, software issue etc. The cluster software automatically detects the failure events and redistributes the data from the failed nodes between the active nodes to keep the whole database available for identification requests. Naturally, this functionality requires to have larger number of nodes than the minimum needed for the specified performance and/or capacity, so there are some reserve for replacing the failed nodes.
High availability – two clusters of MegaMatcher Accelerators may be run in parallel, keeping the data synchronized between the clusters. This configuration provides twice the performance while both clusters operate normally. If one cluster becomes unavailable, the other will continue operation and provide the standard level of performance.
Peer-to-peer architecture – the cluster nodes automatically distribute biometric database and requests from clients between themselves. This architecture means that there are no master node in the cluster, therefore there are no issues with single point of failure or bottleneck.
Nonstop operation – there are no downtime while new nodes are being added to the cluster or one of the nodes disappears. The normal system operation is not interrupted.
Send us an email on
[email protected]