Chemist suggests sweat analysis for biometric authentication

A concept paper published in ChemPhysChem proposes a new biometrics-based authentication approach for unlocking mobile and wearable devices that relies on analyzing skin secretions, or sweat, to build an amino acid profile that is unique to the device’s owner, according to a report in Skin secretions contain many small molecules that can each be targeted for authentication analysis. The profile would be stored within the device and used for identification purposes each time an attempt to unlock is made.

DHS S&T to host series of biometric technology rallies

The U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T) is hosting a series of Biometric Technology Rallies aimed at supporting industry innovation and advance technologies that assist DHS and Homeland Security Enterprise (HSE) operations. DHS will use the results of these rallies to inform planning activities by sharing the information with industry participants to improve product capabilities, as well as with researchers to enable the development of next-generation capabilities. The first Biometric Technology Rally will be held

Researchers find multiracial facial recognition system offers greater accuracy

The University of Surrey has developed a multiracial facial recognition system that delivers more accurate results than other systems typically used. As detailed in Pattern Recognition journal, the 3D morphing face model ‘learns’ from different racial faces to more effectively identify people in 2D pictures – even if an individual’s appearance is affected by their pose, expression, lighting or poor image resolution. Though many facial recognition systems already adapt 3D models to 2D faces found in pictures, most systems use

Global Good Fund, Element to develop biometric ID tool for infants and children

Biometric software developer Element Inc. has partnered with the Global Good Fund to develop a smartphone-based, non-touch biometric platform capable of using unique biological identifiers of infants and children to verify their identity. On a global level, nearly one in four children under the age of five are not registered at birth and lack formal identification. The partnership will extend Element’s existing adult identity platform to this age group, enabling health systems to recognize and track health information of patients

Rutgers engineers develop finger vibration-based access system

Engineers at Rutgers University have developed VibWrite, a smart access system that senses finger vibrations to verify users, according to a report by TechExplore. The low-cost vibration-based authentication system could eventually be used to secure access to homes, apartment buildings, cars, and appliances. “Everyone’s finger bone structure is unique, and their fingers apply different pressures on surfaces, so sensors that detect subtle physiological and behavioral differences can identify and authenticate a person,” said Yingying (Jennifer) Chen, a professor in the

DNA analysis techniques could dramatically improve facial recognition accuracy

The techniques of genomic analysis could be applied to facial recognition to substantially increase accuracy, according to an article by Associate Professor of Pattern Recognition at Kingston University Jean-Christophe Nebel in The Conversation. Nebel sights the use of facial recognition by UK police at the Notting Hill Carnival in August, which resulted in approximately 35 false matches and one “erroneous” arrest, as typical of the accuracy limitations of current facial recognition technology when dealing with “real-life situations.” The effectiveness of

AimBrain patents process for improving accuracy in biometric authentication

Biometric Identity as-a-Service (BIDaaS) platform developer AimBrain was awarded a UK patent for its technical process that enables greater accuracy in biometric authentication. The GB2539705 (A) patent covers a process that allows a user to be authenticated based on the way they look, sound and behave across a wide range of scenarios, by clustering distinctive data and generating a wide range of context-based templates for an individual. Based on several years’ research and development into deep learning and biometric modelling,

New fingerprint tech capable of detecting traces of drugs, blood, alcohol and more

Research teams at Sheffield Hallam University have been collaborating with West Yorkshire Police since 2012 in testing new technology that uses a form of mass spectrometry to find traces of different substances within a fingerprint, according to a report by The BBC. The technique is close to becoming admissible as evidence in court, with the Home Office recently confirming it could be “only months” before the technology is used in casework. Researchers have said that the advanced fingerprinting technique can

Alibaba invests US$15B in overseas research hubs for AI, fintech

Alibaba Group Holding Ltd is investing US$15 billion to establish overseas research hubs to work on artificial intelligence (AI), quantum computing and fintech, according to a report by BNN. The Alibaba ‘Damo’ academy will comprise of eight research bases in China, Israel, the United States, Russia and Singapore, for which the company will hire 100 researchers. “The Alibaba DAMO Academy will be at the forefront of developing next-generation technology that will spur the growth of Alibaba and our partners,” Jeff

Leti and partners develop pressure-based fingerprint sensor

European R&D project known as PiezoMAT (PIEZOelectric nanowire MATrices), comprised of Leti, an advanced-research institute within the CEA Technological Research Division, and several partners, has developed a pressure-based fingerprint sensor with a resolution that’s more than twice as high as current U.S. Federal Bureau of Investigation (FBI) requirements. The project’s proof of concept demonstrates that a matrix of interconnected piezoelectric zinc-oxide (ZnO) nanowires grown on silicon can reconstruct the smallest features of human fingerprints at 1,000 dots per inch (DPI).