Airport check-in may change forever if
Other 3D systems — requiring 16 shots of the face — have proved unworkable because of the time it takes to construct a picture. The chance of movement during such a multi-shot process is extremely high, and if the face moves even a fraction then the 2D to 3D image is unworkable.
MERI also claims several other advantages for its technology. Hardware requirements are a projector and a single camera, making set-up inexpensive — a few hundred pounds, compared with up to £40,000 for older systems. These need at least three or four cameras to capture an image, which means time-consuming parameters and complex calibrations.
Traditional 2D methods measure the distance between eyes, nose and lips, taking several distance measurements then com- paring them. This works well if you can control everything, particularly illumination and movement. The MERI system takes ‘real’ measurements, such as the distance over the surface of the face rather than from one line to another.
This makes the technology more robust and enables it to extract 40-100 parameters rather than the six that the older systems needed.
Possibly the most dramatic breakthrough is the speed at which the light passes over the face — just 40 milliseconds — an innovation that enables a high throughput of 3D face imaging. The system could be used like a metal detector, capturing a number of images in three or four seconds as a person walks through. The best image will be chosen automatically. The speed of the process will open up new applications in security and authorisation.
The research is timely. In two years’ time everyone applying for travel or immigration documents will, by law, also have to register for a national identity card.
It is widely believed that these will include biometric data — fingerprints, iris scans and, very possibly, 3D facial imaging information. A biometric ID card was taken a step closer to reality when home secretary Charles Clarke tested MERI’s split-second system on a recent visit to
The next step is infrared testing. This adds a third dimension MERI wants to explore: utilising the system in industrial applications for monitoring and control. ‘Objects can go on a conveyor belt and, instead of using a flat image, a 3D image can help locate defects in them. Although we are focusing on security applications now, there is great potential in the future,’ said Rodrigues.
The testing remains in its early stages. The team has trialled the system on a small database of 40-50 faces, with 100 per cent accuracy. ‘My quest now is to raise resources to build several systems and test on a large database,’ said Rodrigues. This will involve a database of 10,000 faces, comparing results with 2D face imaging.
The next stage depends on money. The project is funded internally and by a small amount from the Regional Development Agency, Yorkshire Forward. MERI requires industry involvement to continue.
‘We are not a manufacturer, and we need an electronics company to take the ideas forward, to implement and establish them,’ said Rodrigues. The university is talking to firms in