Shanghai researchers create AI system detecting criminals from face features

Two scientists from Shanghai Jiao Tong University have published a controversial new study that uses an AI system to distinguish a criminal from a law-abiding citizen with a 85.5% accuracy rate, according to a report by the Telegraph. Researchers Xiaolin Wu and Xi Zhang collected 1,856 ID photos of Chinese males ages 18 to 55, with no facial hair, no facial scars or other markings. Of this data set, 730 were images of criminals which were provided by the police.

Biometric authentication to be used in over 600M mobile devices by 2021: Juniper Research

Juniper Research has released a new study which finds that biometric authentication is ready to move beyond fingerprints alone and use several different identifiers, including facial recognition and voiceprints. These authentication methods will become part of more people’s lives, they will increase from being installed on an estimated 190 million mobile devices in 2016 to exceed 600 million devices by 2021. The new research, Mobile Biometrics: Consumer Markets, Opportunities & Forecasts 2016-2021, finds that demand from businesses for authentication methods

University of Kent receives EU grant for mobile biometrics research network

University of Kent’s The School of Engineering and Digital Arts has been awarded a €2.5 million (US$2.76 million) grant from the European Commission for a research network that will address current issues facing the use of mobile devices to deliver biometric solutions. The Marie Skłodowska-Curie Integrated Training Network (ITN) grant, which will begin this January, is being spearheaded by Kent’s Deputy Head of Engineering and Digital Arts, Dr Richard Guest. The project will be a collaboration with four other European

Increased use of facial recognition driving demand for IR LED devices

Digitimes Research released new research that finds that among all biometric technologies, the growing use of facial recognition is expected to drive demand for infrared (IR) LED devices, which is used to improve accuracy of facial recognition. The increased application of facial recognition can be attributed to the technology’s contactless nature, quick recognition and ease of use. Digitimes Research notes that while fingerprint recognition remains the most popular biometrics technology, it requires contact of fingers and therefore is mostly applied

Technavio identifies top 4 trends affecting biometrics in BFSI through 2020

Technavio has released a new research report on the global biometrics market in the banking, financial services and insurance (BFSI) sector, which analyzes the most important trends expected to impact the market outlook from 2016 to 2020. The report finds that the global biometrics market in the BFSI sector is projected to see a CAGR growth of close to 20% over the forecast period. Technavio ICT research analysts identifies the top four emerging trends driving the global biometrics market in

Researchers awarded grant to continue investigations into brain biometrics technology

Researchers at Binghamton University, State University of New York (SUNY) have received a $900,000 grant from the National Science Foundation to continue investigations into the next-generation of brain biometric technology. The project, “Brain Hacking: Assessing Psychological and Computational Vulnerabilities in Brain-based Biometrics,” will research the security vulnerabilities of brainprint biometrics and, more specifically, assess the strengths and weaknesses of brain biometrics, principal investigator Zhanpeng Jin said. Jin is the assistant professor of electrical and computer engineering at the Thomas J.

MSU researchers collecting infants’ fingerprint data in India

Researchers from the Michigan State University (MSU) Biometrics Research Group are spearheading a new project that allows researchers and medical workers to receive key information from a single finger scan, according to a report by The State News. Through the project, medical employees will be able to accurately identify children by scanning their fingerprint. The workers will receive key patient information such as recent immunizations, and ultimately be able to determine if the child is malnourished. The fingerprint recognition system

Study finds hair protein effective as identifier

Fingerprints, voice recognition, DNA, and iris scanning are well established as effective methods of accurate identification, but hair protein may be the next frontier for biometrics. Scientific research website PLOS One recently published the article “Demonstration of Protein-Based Human Identification Using the Hair Shaft Proteome,” which gives an indication of the potential for hair protein as a biometric authenticator. Researchers analyzed hair samples from 76 people, and found 185 distinct amino acid patterns. Based on these patterns they were able

Researchers train software to recognize pixelated faces

A team of scientists at the University of Texas at Austin and Cornell Tech have trained software to read or see what’s meant to be hidden in images, enabling it to read blurred or pixelated images of human faces, according to a report by Wired. The researchers said that they didn’t need to develop extensive new image uncloaking methodologies to perform these procedures. Instead, they discovered they could use mainstream machine learning methods in which they trained a computer with

SAS Lab experimenting with palm scanning to improve travel process

SAS Lab, the innovation hub from the Scandinavian airline, is developing various biometric identification technologies to improve the overall travel process, according to a report by TNooz. The innovation hub believes that palm scanning will likely be the most reliable of all the biometric technologies available on the market because other technologies are either susceptible to forgery or uncomfortable for passengers to use on a regular basis. “Overall, I’ve been a little bit concerned over biometrics – the problem is