3D Face Imaging in 40 Milliseconds

Roland Piquepaille writes "Computer scientists at Sheffield Hallam University, UK, have developed a new face recognition software which can produce an exact 3D image of a face within 40 milliseconds. A pattern of light is projected on your face, creating a 2D image, from which an accurate 3D representation is generated. This technology should speed airport check-ins, but it could also be used in banks or for checking ID cards as it allows full identification in less than one second."

at best, incremental

[penguin-collective]

3D-based face recognition has been tried before, and you can buy 3D scanners that use projected light patterns commercially. So, there isn't really anything particularly new about this.

Re:database?

[Anonymous Coward]

Hey, even without a shave, existing facial rec systems have been known to fail when the lighting at pickup time differs from that of recording time. Face rec is hardly new, but the problem hasn't been speed, AFAIK. The Mass. cops tried it and quietly folded their tents.

Re:This Is A Good Thing

[Anonymous Coward]

Your behind the times by five years:

Face Recognition at Florida Superbowl [howstuffworks.com]


A ticket to Super Bowl XXXV in Tampa Bay, Florida, didn't just get you a seat at the biggest professional football game of the year. Those who attended the January 2000 event were also part of the largest police lineup ever conducted, although they may not have been aware of it at the time. The Tampa Police Department was testing out a new technology, called FaceIt, that allows snapshots of faces from the crowd to be compared to a database of criminal mugshots.


And the results:
The Register on Face Recognition software [theregister.co.uk]

By leveraging the Florida open-records law, the watchdog organization obtained system logs proving that the Visionics contraption has thus far failed to identify one single crook or pervert listed in the department's photographic database, while falsely identifying 'a large number' of innocent citizens.

"The earliest logs provided by the department show activity for July 12, 13, 14, and 20, 2001. On those dates, the system operators logged fourteen instances in which the system indicated a possible match. Of the fourteen matches on those four days, all were false alarms," the ACLU notes.

The Tampa coppers started using the system in June of this year, and abandoned it in August.

3D Faces - The Movie

[0x15]

If this interests you, MERI has additional information in the form of a movie [shu.ac.uk] about it.

Even worse...

[John Harrison]

The article implies that you have to be enrolled using this system in order to it to be used to verify your identity. So it isn't any use in finding those that there is a high resolution photograph of without the 2d pattern projected on them to generate the 3d surface. This is only useful for proving that someone is carrying their own valid document, not for picking known criminals out of crowds.

You wanna something foolproof ?

[aepervius]

Here is it :
Combine together two of those :
* iris recon
* 3d face recon
* fingerprint
with one of those :
* a pin code
and one of those :
* a secure card with a chip and a recent encryption technology

As it is always said here on /., something you are, something you have, something you know.

Deceptive News Article

[NewsSmellsFishey]

Hello, first post and all. Saw this news article and it made me laugh. 40ms for taking the picture, maybe, but that doesn't include all the other time involved. I'm a student at Sheffield Hallam and I've been taught by the lecturers involved. What's more I've had my face scanned in. I can tell you that 40ms is very, very deceptive. So maybe it does take 40ms to take the photograph but it isn't a stunningly high resolution photo and even then it is only a photo. The system works by taking a normal photograph and scanning your face separately. The two are put together later in post-processing and from my experience it takes several days of fiddling with parameters, avoiding marking assignments and not paying attention to students. I wanted the data for my face from when it had been scanned. It took me nearly a week of nagging to get the lecturers involved to sort it out and in the end I had to get it off their computers myself (an old mac). 40ms doesn't really include the time it takes for you to cut through the bureaucracy of Sheffield Hallam

Re:database?

[Dashing Leech]

"Uh, yeah, because facial recognition software is so accurate."

Actually, I've worked on 3D facial recognition algorithms and they can be incredibly accurate. You are correct that 2D facial recognition algos have limited accuracy, but that's largely because 2D cameras merely measure the amount of light reflected into each pixel, so any real-world dimensional measurement is an interpretation of feature locations and extrapolated into 3D. Perspective views is big problem as are lighting conditions, clutter, and disguises.

A 3D sensor directly measures the 3D shape and can fit it quite easily to the reference model. We've done 3D face matches with wigs, glasses, and beards at the same time and still correctly identified the person. You really have to cover up a significant amount of the shape of the face to fool it.

And even then, that was for identification. This application is verification, so a disguise would be counterproductive. You'd have to take someone with a similar face shape and use professional face-shaping make-up (like for movies) to make an identically-shaped face to fool it into believing you were someone you were not. Not just one that looks the same, but is actually the same size and shape. Hard to do, especially without someone clearly seeing you are wearing the fake features, despite what Mission Impossible or other movies make us believe.

That being said, I don't know the statistics on similarities of faces. I would certainly bet identical twins could fool it, though I'm not sure how identical their face shapes are statistically.

Re:exact?

[Anonymous Coward]

Sure, it's from Roland, however, he doesn't link to his own site this time, despite doing his own writeup about the technology.

Hurrah for just ignoring something without taking a critical look at it.