Either fingerprint or iris mode can be used as a primary form of identification or both fingerprint and iris modes can be used together as a multi-biometric solution. MegaMatcher Accelerator also can check identification results with other biometric data from any Neurotechnology-supported modality, including face, palmprint or voice identification. Unlike systems that use pre-classification or internal database indexing, MegaMatcher Accelerator can perform a full database search for each match. This eliminates potential false rejections from incorrect classifications and gives MegaMatcher Accelerator a very high degree of reliability.MegaMatcher Accelerator 5.0 includes an improved fingerprint algorithm that is tens to hundreds of times faster, depending on fingerprint type (plain, rolled, paperscan, etc.), yet can reach the same accuracy level as MegaMatcher SDK – the most accurate AFIS product from Neurotechnology – when set at the typical False Acceptance Rate (FAR) values and template size used in medium and large scale projects. Unlike systems that achieve higher speeds by applying constraints, such as limiting maximal rotation of two compared fingerprints, MegaMatcher Accelerator 5.0 maintains its high speed remaining fully rotation invariant.
- MegaMatcher Accelerator 5.0 Extended Version offers the highest performance for applications that require extremely fast matching with a large volume of data. Working on an HP ProLiant DL360p G8 server with 128 GB RAM, MegaMatcher Accelerator 5.0 Extended can manage a database of up to 40 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 5.0 Standard Version is a fast, cost-effective, PC-based solution for customers with smaller biometric applications. Working on a PC with an i7 processor, 16 GB RAM, 1.5TB HDD, MegaMatcher Accelerator 5.0 Standard can manage databases of up to 5 million irises or 4 million fingerprints and can perform matching of up to 35 million fingerprints or 70 million irises per second.