FB

Can you please provide our readers with a brief background of the company?

IN

Neurotechnologija provides algorithms and software development products for biometric fingerprint and face recognition, computer-based vision and object recognition to security companies, system integrators and hardware manufacturers. More than 1400 system integrators and sensor providers in more than 60 countries license and integrate Neurotechnologija's technology into their own products.

Drawing from years of academic research in the fields of neuroinformatics, image processing and pattern recognition, Neurotechnologija was founded in 1990 in Vilnius, Lithuania and released its first fingerprint identification system in 1991. Since that time Neurotechnologija has released more than 30 products and version upgrades for identification and verification of personal identity.

With a combination of fast algorithms and high reliability, Neurotechnologija's fingerprint and face biometric technologies can be used for access control, computer security, banking, time attendance control and law enforcement applications, among others.

In 2004 Neurotechnologija began research in artificial intelligence (AI) and mobile autonomous robotics fields, and in the same year the company's AI division was founded. The division's first product, SentiSight computer-based vision and object recognition technology, can be used in a variety of applications including image search engines, security systems, manufacturing and robot and machine vision.

FB

You provide algorithms and software development products for biometric fingerprint and face recognition. Can you review your Biometric product lineup?

IN

Because our algorithms are core technologies for the development of biometric applications, we offer our products in software development kit (SDK) form. Our customers create solutions and/or end user products based on our SDKs.

We are offering fingerprint and face development kits that range from embedded to large scale applications.

For embedded applications we offer FingerCell EDK for fingerprint recognition and FaceCell EDK for facial recognition. Both of these products are designed for use in various embedded or mobile hardware, smart phones, PDA, handheld computers and other devices.

For PC applications we offer VeriFinger SDK for fingerprint recognition and VeriLook SDK for facial recognition. Both SDKs allow easy integration and rapid development of biometric applications using functionality from the VeriFinger/VeriLook recognition algorithms. These algorithms provide high identification reliability, 1:1 and 1:N matching modes and comparison speeds of up to 40,000 fingerprints per second using VeriFinger and up to100,000 faces per second using VeriLook. The integrator has complete control over SDK data input and output, therefore SDK functions can be used in connection with any scanner/webcam, any database and any user interface. Both VeriFinger and VeriLook SDKs support Microsoft Windows, Linux and Mac OS X operating systems.

For large scale applications we offer MegaMatcher SDK. It is intended for the development of large-scale AFIS and multi-biometric face-fingerprint identification systems. The MegaMatcher technology is MINEX-certified and allows the use of either a fused face-fingerprint recognition algorithm or fingerprint and facial recognition engines separately. The fused algorithm matches up to 400,000 records per second with outstanding reliability. MegaMatcher SDK contains essential components required for large scale applications, including:

1. fast and reliable fingerprint and face recognition algorithms and their fusion
2. fault-tolerant scalable cluster software which provides fast parallel matching, processes a high number of identification requests and handles databases with practically unlimited size
3. biometrical standards support required for data interchange between biometrical systems. The following standards are supported: WSQ, ANSI/NIST ITL-1-2000, ANSI/INCITS 378-2004 and ISO/IEC 19794-2.
4. API for latent fingerprint template editing which allows MegaMacher SDK to be used not only for civil AFIS applications but also in forensic AFIS applications.

FB

Neurotechnologija has always performed well in the biometric competitions, including the International Fingerprint Verification Competition. Can you elaborate on this success?

IN

Our success is based more than 17 years of ongoing research in the field. We have dedicated research teams who are continuously working on new products and features.

Recently our technologies were evaluated in MINEX and the International Fingerprint Verification Competition (FVC2006).

MegaMatcher 2.0 is one of only 12 algorithms worldwide to receive full MINEX certification for both fingerprint template encoding and matching. This certification puts MegaMatcher 2.0 SDK into the U.S. government buyers' certified list of fingerprint recognition algorithms.

With the rapidly growing demand for automated fingerprint identification systems for both civil and forensic applications, the MINEX certification is on the critical path for companies that want to market their technologies and show conformance to the strictest standards for fingerprint recognition.

In FVC2006 we achieved the highest ranking when using the most realistic benchmark for real-world biometric applications, "Average Zero FMR," and we also won four gold medals, two silver and two bronze medals in Open Category.

Our algorithm took second place in the FVC2006 Light Category, according to the Average Zero FMR benchmark. The algorithm won one gold and four bronze medals in this category.

FB

Are you investigating adding any additional biometric types to your lineup?

IN

Of course, our research is not limited only to fingerprint and face technology. Palm prints, voice and iris recognition are also research areas we are interested in. It is possible that we will add one or all of these types into our product lineup in the future.

FB

What do you see as the greatest challenge to the Biometric Industry today?

IN

One of the biggest challenges to the Biometric Industry is the high cost of most large-scale multi-modal systems. These systems are usually very expensive and considered to be out of reach for many projects. However, we believe it should be possible to build such systems using lower costs components, for example using regular PCs instead of high costs servers. All development processes should be easy and fast. In our products we strive to achieve these goals.

FB

As a global player, where are you seeing the greatest growth in the biometric space?

IN

We see face recognition and large scale multi-biometric demand increasing around the globe as more and more countries decide to build national IDs, biometrical passports or voting systems. Biometrical technologies are core for all of these applications.

As systems are targeted for bigger and bigger audiences, requirements for accuracy and speed are also increased. Single biometric types (fingerprint or face) can not satisfy these requirements. Multi-biometric systems are required for such applications. In the near future we can expect to see a larger demand for multi-biometric technology.

FB

Has this been a good year for the company?

IN

Indeed, this year has been successful for our company. In the past 12 months we have released new versions of several products, including: VeriFinger 5.0 (September 2006), VeriLook 3.0 (October 2006), FingerCell 2.0 (January 2007) and 2.1 (July 2007) and MegaMatcher 2.0 (January 2007). We also introduced two new products – FaceCell, in January and SentiSight, our first universal object recognition technology for robotics and computer vision applications.

MegaMatcher 2.0 received full MINEX certification this year and we continued to perform well in biometric algorithm competitions. Our large-scale technology was selected for jail attendance, student/staff enrollment and verification in national size systems. Throughout this year we have observed a constant increase in the demand for biometrical systems, which has lead to better sales for our company.

back