Anixter supports biometrics systems with unique lab

The development and adoption of advanced security technologies puts pressure on businesses to not just understand them, but to communicate them to clients. For this reason, Anixter supports the growth of its biometrics products distribution business with a unique laboratory at its Glenview, Illinois headquarters. The Anixter Infrastructure Solutions Lab is used to demonstrate the effectiveness of different technologies in different situations and configurations, to help systems integrators and end users choose the most effective products and configurations for their

iBeta broadens options for accredited independent biometric testing

Biometrics companies may have more options than they realize to improve their technologies and prove their credibility by testing them against established standards. Different standards for biometrics application performance are still evolving, along with the technology and markets for those applications. A standard originally set for Electronic Prescription of Controlled Substances (EPCS) is benefiting a growing number of companies, including ones that do not offer technologies for that particular application, says Gail Audette, quality manager for leading independent testing firm

iBeta wraps up spoofing and liveness testing project

iBeta Quality Assurance, a full-service biometrics, software quality, security, and performance testing lab, recently completed a successful project for a mid-sized bank to evaluate the False Accept Rate (FAR), False Reject Rate (FRR), and Spoof False Accept Rate (SFAR) of several biometric subsystem vendors’ products across multiple modalities. “Spoofing and liveness testing is an increasingly important part of any thorough evaluation of biometric technology as black hats look for new ways around improved biometrics-based security,” said Dr. Kevin Wilson, Director

NEC’s video face recognition technology achieves top results in NIST testing

NEC Corporation announced that its face recognition technology achieved the highest performance evaluation in the recent Face in Video Evaluation (FIVE) testing performed by the U.S. National Institute of Standards and Technology (NIST). NIST released the results in its Interagency Report 8173: Face In Video Evaluation (FIVE) Face Recognition of Non-Cooperative Subjects. The company’s face recognition technology achieved the top ranking for the fourth consecutive time following the 2009 Multiple Biometric Grand Challenge (MBGC 2009), 2010-2011 Multiple Biometrics Evaluation (MBE

EAB lobbies EU Parliament to enhance biometric testing

The European Association for Biometrics (EAB) sent a letter to the European Parliament last month requesting legislation to enable easier access to data required for testing biometrics products and systems. The Management Board and Advisory Council of the EAB stated that it believed an “overly restrictive and non-harmonized legal infrastructure hinders the testing of biometric systems and products for large scale settings, even when applying appropriate safeguards.” The letter notes that “due to the lack of proper provisions the owners

PING AN Tech facial recognition receives high score in latest LFW test results

PING AN Tech achieved a high score in the latest tests conducted by the University of Massachusetts’ facial recognition technology benchmark Labeled Faces in the Wild (LFW), scoring a face recognition ratio of 0.9960+/-0.0031. The company has been developing the face recognition technology over the past three years, with its business units repeatedly using the application. PING AN Tech’s 13 professional companies and 55 partners all tested the application, including Ping An iLoan 2.0, Ping An Life Insurance, and Shenzhen

iBeta introduces three new performance scan testing packages

Software quality, security, performance and biometrics testing lab iBeta Quality Assurance has released three new web-focused load/performance testing packages designed to reduce the high cost and complexity that is typically associated with load testing scenarios. The company developed the performance scan packages in an effort to meet the growing customer demand for focused-scope, fixed-cost load testing. The first performance scan package is QuickScan, which is a web page retrieval at increasing load levels to evaluate scalability. The second package is

Hoyos partners with NIST to improve gov’t evaluation of contactless fingerprint capture devices

Hoyos Labs has partnered with the National Institute of Standards and Technology (NIST) to develop new ways to measure the image fidelity of contactless fingerprint capture devices to be considered for inclusion on the U.S. government’s Certified Product Lists. In law enforcement, the most commonly used fingerprint scanning devices digitally capture a fingerprint pressed on a glass surface with livescan technology. These devices present the notable disadvantages of taking extra time and hygienic issues. To address these concerns, law enforcement

Sighthound boasts LFW benchmark results for its facial recognition software

Sighthound, Inc. announced that its facial recognition system ranks first – with an accuracy of 99.79% – against the Labeled Faces in the Wild (LFW) benchmark database hosted by the University of Massachusetts. Previous highest accuracy scores include Google at 99.63% and Baidu at 99.77%. The company says that its facial recognition system stands out by using less than 2% of the amount of training data used by Google, and by using only one crop per image. Others on the

Russian startup tops UW facial recognition challenge

Russian startup N-Tech.Lab recently became a leader in the MegaFace challenge in face recognition algorithms at the University of Washington. N-Tech.Lab uses advanced techniques in the field of artificial neural networks and machine learning to develop its software products. The company’s facial recognition algorithm extracts the characteristic features of a person’s face from a picture. N-Tech.Lab’s solution was declared the most accurate for the FaceScrub search in large datasets, achieving 73.3% accuracy on 1 million faces. Google’s Facenet and Beijing