Page 27 - Security Today, July/August 2019

“A number of challenges have had to be solved to bring biometrics to the door. ”
By Stephen Carney
metrics sensor features several core compo- nents including an embedded processor that analyzes the raw imaging data to ensure that the sample being imaged is a genuine human finger rather than an artificial or spoof material. Advanced machine learn- ing techniques can be used so the solution can adapt and respond to new threats and spoofs as they are identified. This is criti- cal if biometrics is to eliminate the need to use PINs or passwords. It also protects privacy—if you can’t use a fake finger, then even if you did obtain someone’s fingerprint data, it is meaningless.
Optimized performance. The top-per- forming solutions capture usable biometric data on the first attempt for every user and speed the liveness detection process. They quickly perform template matching to reject impostors and match legitimate users and should be tested by skilled and independent third parties like the National Institute of Standards and Technology (NIST) for in- teroperability so that performance is based on data that can be trusted in all template- matching modes.
Raw performance is not enough, how- ever—this performance must be trusted. The next generation of solutions deliver trusted performance by using the top-ranked NIST certified MINEX III minutia algorithm to ensure interoperability with industry- standard fingerprint template databases in all template-matching modes. This includes both template-on-card and card/mobile + finger modes using “1:1” template-matching profiles, as well as template-on-device mode for finger-only authentication using “1:N” matching. Delivering this level of interoper- ability ensures that today’s systems, which are based on much more powerful hardware than in the past, will perform accurate 1:N identification of a full database in less than a second, significantly reducing delays and the queues users often experienced with earlier biometric solutions.
Deployment Best Practices
Organizations now have an easy path for taking their systems from traditional read- ers to a biometric solution but they should adhere to several important best practices during deployment. Biometrics must be in- corporated into access control systems using
and user convenience it offers, is driving in- terest in marrying biometrics with physical access control applications.
Environment isn’t the only challenge that has faced the use of biometrics in access control applications. Many fingerprint tech- nologies are vulnerable to spoofs and hack- ing, enabling fraudsters to create a fake fin- gerprint and present it to a reader. Previous solutions also have been notoriously slow at moving users through doors as compared to using a simple ID card and reader. There also have been significant differences in the
performance between available fingerprint capture technologies.
Key developments in biometrics are re- moving these issues and shining a spotlight on the technology and its suitability for use in access control.
Better image capture. The quality of the captured image is critical, across all types of fingerprints ranging from children to the elderly, and in cold, dry, dirty and wet environments. To address these challenges, organizations are increasingly choosing sensors that use multispectral imaging that optimizes the quality of the captured image by illuminating the skin at different depths. This enables the sensor to collect informa- tion from inside the finger to augment avail- able surface fingerprint data.
Also important, the sensor collects data from the finger even if the skin has poor contact with the sensor because of such environmental conditions as water or fin- ger contamination. Multispectral sensors have been proven to work for the broadest range of people with normal, wet, dry or damaged fingers, across the widest range of conditions, from the presence of lotions or grease to sunlight, wet or cold conditions. The sensors also resist damage from harsh cleaning products and contamination from dirt and sunlight.
Liveness detection that enhances trust. Even when fingerprint images are properly captured, if they are a plastic fake or other artificial copy, the system cannot be trusted. For this reason, liveness detec- tion is an increasingly visible dimension of biometric performance in commercial ap- plications. While liveness detection is critical for preserving trust in the integrity of bio- metrics authentication, it must not impede performance or result in excessive false user rejections. The most trusted multispectral imaging fingerprint sensors with liveness detection provide a real-time determina- tion that the biometric data captured by the fingerprint reader is genuine and being pre- sented by legitimate owners, rather than someone impersonating them.
This capability leverages the image- capture approach of using different colors or spectrum of light to measure the surface and subsurface data within a fingerprint. In addition to this optical system, the bio-
WWW.SECURITYTODAY.COM 27
Alexander Supertramp/Shutterstock.com