Free newsletter Subscribe
NewScientist.com home page Latest science & technology news Hot topics in science Q & A's from everyday science Feedback, letters, book reviews, interview Links to other science sites Contents of this week's print edition Subscribe to New Scientist magazine New Scientist magazine archive Search 1000's of science and technology jobs
All the latest news
Conference News
Search News

Top Stories

[Subscribe to New S]
 • Subscribe
 • Renew
 • Change address

Top Science Jobs

The World's No.1 Science & Technology News Service

Smart software makes sense of rough sketches

17:47 12 September 03
Exclusive from New Scientist Print Edition. Subscribe and get 4 free issues.

Intelligent software that brings rough sketches to life in a virtual world is promising to revolutionise the way children learn and to help engineers visualise their designs.

In designing the software, developers at the Massachusetts Institute of Technology have had to tackle several tough tasks. First the software must recognise crude hand-drawn shapes in the way the user intended for example, by spotting that four wiggly lines represent a square with straight sides.

Then it has to recognise the context of the objects being sketched, in the same way that we interpret two circles under a box on a slope as some kind of vehicle on wheels. Finally, the package has to animate the sketch so that objects move as they would do in the real world.

 Animating sketches
Animating sketches

Current sketching software only recognises the geometry of a sketch - for example, that two lines meet at a specific angle - and cannot recognise context at all.

Allocation and adjustment

The MIT software monitors the image as it is being drawn on to a computer screen and allocates probabilities to various interpretations of what it might represent.

As the user adds more detail, the software adjusts these weightings. To do this, it uses a technique known as Bayesian analysis, which is normally used to compute the likelihood of specific causes, given certain effects.

More on this story
Subscribe to New Scientist for more news and features

Related Stories

For more related stories
search the print edition Archive



"With our software, the 'causes' are what the user had in mind to draw, and the 'effects' are what was actually drawn," says Randall Davis, who has developed the code with Christine Alvarado at MIT's Artificial Intelligence Laboratory.

Once the computer has settled on an interpretation, it applies the laws of physics such as gravity and friction to set the virtual world in motion. Cars roll down hills, pendulums swing, and objects bang into each other.

The Bayesian part of the software is still at an early stage: it recognises only squares. Davis's next goal is to get it to recognise a much broader range of crudely drawn shapes.

Part of the problem is thinking up all the possible ways someone might draw a shape, so as to be able to assign realistic probabilities to particular patterns on the screen.


Celeste Biever


Print this article Send to a friend

Subscribe to New Scientist Magazine

For more exclusive news and expert analysis every week subscribe to New Scientist print edition.

  For what’s in New Scientist magazine this week see Print Edition
  Search the Archive for more stories like this, originally published in the Print Edition
  Subscribe to New Scientist Print Edition
  Contact us about this story
  Sign up for our free newsletter
[Subcribe to New Sc]

Global Warming
Quantum World
Fast TCP promises super-quick movie downloadsNews
Tweaking a protein that makes cells sticky could control cancerNews
Why is the ratio of men to women roughly equal?Last Word

Elsewhere today
All the best science stories from the web

New Scientist Archive
About newscientist.com •  Subscribe •  Contact Us •  FAQ •  Media Information •  Disclaimer •  Terms and Conditions •  Site Map •  Privacy Policy  © Copyright Reed Business Information Ltd.