Maastricht Economic and social Research and  training centre on Innovation and Technology

 
I&T Weekly holiday break
I&T Weekly is taking a holiday break. We will be back on Friday, January 12, 2018 with a fresh selection of innovation and technology news. On behalf of the entire UNU-MERIT team, we wish our readers an excellent 2018!




Subscribe and receive
I&T Weekly by email
 
email address

text
html


Please type the above code:
 
All headlines
  • France announces landmark ban on fossil fuel production
  • Extreme laser bursts may lead to practical nuclear fusion
  • Gene editing staves off deafness in mice
  • Integrated circuits could make quantum computers scalable
  • 'Water cloak' uses electromagnetic waves to eliminate turbulence
  • Cold cigarette lighter will power satellite
  • Even a mask won’t hide you from the latest face recognition tech
    Face recognition software can now see through your cunning disguise – even you are wearing a mask.

    Researchers from the University of Cambridge trained a machine learning algorithm to locate 14 key facial points. These are the points the human brain pays most attention to when we look at someone’s face.

    The researchers then hand-labelled 2000 photos of people wearing hats, glasses, scarves and fake beards to indicate the location of those same key points, even if they couldn’t be seen. The algorithm looked at a subset of these images to learn how the disguised faces corresponded with the undisguised faces.

    The system accurately identified people a wearing scarf 77% of the time – a cap and scarf 69% of the time and a cap, scarf and glasses 55% of the time. This isn’t as good as systems that recognise undisguised human faces, but it is the best at seeing through disguises, according to the researchers.

    The system only needs to be able to see a fraction of facial key points – most of which are around the eyes and mouth – to be able to guess where the other points are likely to be. Based on that guess, it can identify the person if it has already been shown a map of their key points.

    The team aims to take the research even further and see if it’s possible to design an algorithm that can identify someone wearing a rigid plastic mask, like the V for Vendetta masks that are popular at some protests.

    New Scientist    September 07, 2017