This article is from the source 'bbc' and was first published or seen on . It last changed over 40 days ago and won't be checked again for changes.

You can find the current article at its original source at http://www.bbc.co.uk/news/technology-33718803

The article has changed 2 times. There is an RSS feed of changes available.

Version 0 Version 1
Facial recognition tool 'works in darkness' Facial recognition tool 'works in darkness'
(35 minutes later)
Two scientists at a German university have developed a tool which recognises a person's face in complete darkness.Two scientists at a German university have developed a tool which recognises a person's face in complete darkness.
The technology identifies a person from their thermal signature and matches infrared images with ordinary photos.The technology identifies a person from their thermal signature and matches infrared images with ordinary photos.
It uses a deep neural network system to process the pictures and recognise people in bad light or darkness.It uses a deep neural network system to process the pictures and recognise people in bad light or darkness.
However, the technology is not being used commercially yet, with one of its creators, Dr Saquib Sarfraz, saying: "There are no plans to roll it out."However, the technology is not being used commercially yet, with one of its creators, Dr Saquib Sarfraz, saying: "There are no plans to roll it out."
He told the BBC: "We have been doing research on face recognition already for several years and have a scientific interest in the problem. Our presented work on face recognition in thermal images is currently not used outside the research lab." Dr Sarfraz, who worked on the project with colleague Dr Rainer Stiefelhagen at the Karlsruhe Institute of Technology, told the BBC: "We have been doing research on face recognition already for several years and have a scientific interest in the problem.
"Our presented work on face recognition in thermal images is currently not used outside the research lab."
In tests, the technology had an 80% success rate, and worked 55% of the time with one image, and Dr Sarfraz said that "more training data and a more powerful architecture" could produce better results.In tests, the technology had an 80% success rate, and worked 55% of the time with one image, and Dr Sarfraz said that "more training data and a more powerful architecture" could produce better results.
With a higher success rate, the tool could potentially be used by police to catch and identify criminals.With a higher success rate, the tool could potentially be used by police to catch and identify criminals.
'Interesting approach''Interesting approach'
Dr Tom Heseltine, head of research for UK face recognition company Aurora, was impressed with the project.Dr Tom Heseltine, head of research for UK face recognition company Aurora, was impressed with the project.
"It is an interesting approach and a very significant improvement in accuracy," he told the BBC."It is an interesting approach and a very significant improvement in accuracy," he told the BBC.
"Although the ability to recognise faces in the dark is not new, the ability to use thermal infrared and match against a standard colour photograph could open up some new specific applications areas."Although the ability to recognise faces in the dark is not new, the ability to use thermal infrared and match against a standard colour photograph could open up some new specific applications areas.
"Questions may be raised about how susceptible the technology is to variations in body temperature."Questions may be raised about how susceptible the technology is to variations in body temperature.
"Their biggest advantage comes in that they could potentially operate in the dark without the need for active infrared illumination.""Their biggest advantage comes in that they could potentially operate in the dark without the need for active infrared illumination."
Daniel Nesbitt, research director of privacy campaign group Big Brother Watch, was keen to ensure that identification of individuals was undertaken correctly.Daniel Nesbitt, research director of privacy campaign group Big Brother Watch, was keen to ensure that identification of individuals was undertaken correctly.
He told the BBC: "All facial recognition technology has the potential to be very invasive of an individual's privacy if done the wrong way.He told the BBC: "All facial recognition technology has the potential to be very invasive of an individual's privacy if done the wrong way.
"This new research makes it even more vital that facial recognition is properly covered by legislation and that strong safeguards are put in place to protect people from misuse."This new research makes it even more vital that facial recognition is properly covered by legislation and that strong safeguards are put in place to protect people from misuse.
"It is important that a serious and wide-ranging debate about all new technology of this type takes place. Our privacy cannot be forgotten no matter how innovative a new piece of technology may seem.""It is important that a serious and wide-ranging debate about all new technology of this type takes place. Our privacy cannot be forgotten no matter how innovative a new piece of technology may seem."