SecurityWorldMarket

14/12/2010

Megamatcher Accelerator 3.0 for rapid biometric identification

Vilnius, Lithuania

Neurotechnology, a provider of high-precision biometric identification technologies, has released the Megamatcher Accelerator 3.0, a packaged multi-biometric software and hardware solution for high-volume, high-speed fingerprint and iris identification.
This latest version of Megamatcher Accelerator includes very fast iris matching capabilities of up to 200 million irises per second, with increased fingerprint matching speeds of up to 100 million fingerprints per second. Either iris or fingerprint modes can be used as primary, fast-identification biometrics, or both can be used together for even more accurate multi-biometric identification. Additionally, Megamatcher Accelerator can check identification results with other biometric data from any Neurotechnology-supported modality, including fingerprint, iris, face or palmprint, providing the very high level of reliability required for applications such as voter duplication detection, passport issuance, border crossings or other national-scale projects.

Unlike systems that use classification or indexing schemes for matching (which can result in loss of reliability and speed), Megamatcher Accelerator’s matching technology compares every fingerprint and every iris to provide more accurate results. Megamatcher Accelerator 3.0 can manage a database of up to 30 million fingerprints (a 10 million fingerprint increase over the previous version) with speeds that are 2.5 times faster than the 1:N (1-to-many) matching speed of the previous version, making it, according to the company, the fastest, high-volume fingerprint matching engine available. When iris is used, Megamatcher Accelerator 3.0 can manage a database of up to 50 million irises. For situations where an even larger number of fingerprints or irises is required, multiple Megamatcher Accelerators can be connected in a cluster to manage databases with billions of records.

“In the last few years, a number of countries have engaged in very large, national-scale biometric projects that require identification or de-duplication of records for tens or hundreds of millions of people,” said Dr. Algimantas Malickas, CEO of Neurotechnology. “For better reliability, such projects may require not only a single biometric modality, but multi-biometric identification. Megamatcher Accelerator is specially designed for such large-scale applications. Adding fast iris identification and increasing both speed and managed volume allows us to increase the reliability of such systems while decreasing both complexity and pricing,” Dr. Malickas added.

Megamatcher 3.0 is available in both extended and sandard versions. System benchmarks for both Megamtcher Accelerator 3.0 versions are said to be among the fastest in the industry.

Megamatcher Accelerator 3.0 extended version offers the highest performance for applications that require extremely fast matching with a large volume of data. Working on an HP Proliant DL360G7 server with 96GB RAM, Megamatcher Accelerator 3.0 extended can manage a database of up to 30 million fingerprints and perform 1:N matching at a speed of 100 million fingerprints per second; it can manage a database of up to 50 million irises and perform 1:N matching at a speed of 200 million irises per second.

Megamatcher Accelerator 3.0 standard version is a fast, cost-effective, PC-based solution for customers with smaller biometric applications. Working on a PC with an i7 processor, 12GB RAM, 1.5TB HDD, Megamatcher Accelerator 3.0 standard can manage databases of up to 5 million irises or 3 million fingerprints and can perform matching of up to 35 million fingerprints or 70 million irises per second.

Megamatcher and Megamatcher Accelerator technology is available for use in a wide variety of biometric solutions worldwide for election control, passport and visa documentation, border control, criminal investigations and duplicate searches in large-scale government and commercial databases. The Megamatcher fingerprint recognition algorithm is NIST MINEX-compliant for use in US Government Personal Identity Verification programme fingerprint recognition applications and it supports most biometric industry standards.


Product Suppliers
Back to top