According to Andrew Bangham of the School of Information Systems at the University of East Anglia, who is leading the research, the system succeeds where older technology fails because it maintains the high resolution of the image it is viewing while focusing on a specific area of interest.

Other image recognition technology relies on a technique known as filtering. By removing successive levels of detail, the objects in the image are simplified until they appear as basic shapes that the computer can recognise. The problem is that the picture becomes fuzzier as more information is removed, losing the very detail the computer needs for recognition.

“Perhaps it’s because we came late on to the scene that we have stumbled on our different technique,” says Bangham. His process, which is called “sieving”, sifts through the information in the image looking for shapes of specific sizes.

The team’s computer is fitted with a microphone as well as a camera. The camera watches the mouth and grades the lip patterns associated with words according to size. “The O shape of the open mouth is obviously the largest shape and the closed lips at the end of the word the smallest,” says Bangham.

Having “sieved” the shapes, the computer can match them against the sounds the person is making to work out the words. This dual recording overcomes the main problem plaguing purely audio systems—confusion arising from background noise. Recognition is distinctly higher than with either audio or video systems, regardless of noise.

The new system already recognises the letters of the alphabet and simple words such as “yes” and “no” when spoken by 10 different people. “We expect this to be useful within a year at research level,” Bangham says.

‘I think the problem with the C₅,’ he says ‘was that I was
producing something which I didn’t personally need.’ On the other hand,
he needs a good folding bike. He cycles through London and works on the
third floor of a building with an unreliable lift.

The bike will be entirely made of different types of fibres, such as
Kevlar and carbon fibre. These materials are much lighter than the metals
or metal alloys currently used. Sinclair declines to say which fibres he
will use or even if the bike will use a chain to drive the rear wheel. Nor
will he say if it will have pneumatic tyres. But the fact that he is planning
to manufacture all the parts at his own plant suggests that the bike will
have few conventional components.

Past attempts to replace the conventional bike chain with a belt, shaft-drive
or any other system have proved heavy at best and unreliable at worst. Early
tyres were made of solid rubber but these proved both heavy and hard. Inflatable
pneumatic tyres puncture but are light and provide some cushioning against
bumps. John Boyd Dunlop, pioneer of the inflatable tyre, experimented with
cellular tyres which contain a multitude of air pockets, but dismissed them
as they squash on the road and soak up energy.

Similarly, non-metal bikes have failed to catch on. Among the most recent
was one made of plastic from Sweden. ‘If you took those bikes and stripped
off all the plastic and weighed it,’ says Sinclair ‘and stripped off all
the metal and weighed it, the metal would weigh a lot more than the plastic.
So they really weren’t non-metal in the sense that I’m talking about.’

The Sinclair machine will have a conventional riding position. ‘We tried
every variation we could think of,’ he said, ‘and it revealed something
which probably wouldn’t surprise a lot of people but it surprised me, and
that was that the relative positions of the saddle, the handlebars and the
pedals on a bicycle today are pretty much optimal.’ The new bike’s frame
remains secret but, as with other small-wheeled bikes, it is unlikely to
be a traditional diamond shape.

He put a team to work on the project in the early 1980s. The bike they
developed worked well enough but ‘it was 25 per cent lighter than the lightest
bike, which is pretty good but still wasn’t good enough’. Now, with the
project revived, he is looking for a factory to go into commercial production
at the end of next year.

‘I’m not going to replace existing bicycles,’ Sinclair says, ‘because
that’s not what I object to. I want to give people a fresh reason to use
a bicycle, perhaps introduce people to bicycles who might otherwise not
use them because of all the problems. It’ll look nicer and it’ll be more
useful for town riders who are fed up with locking up bikes wherever they
˛ľ´Ç.’