Picture search

A pair of Penn State researchers has developed a new system that one day could make it easier to search for photographs on the internet.

The system works by teaching computers to recognise the contents of photographs, such as buildings, people, or landscapes, rather than by searching for keywords in the surrounding text, as is done with most current image-retrieval systems.

They hope that one day, their so-called Automatic Linguistic Indexing of Pictures in Real-Time (ALIPR) system could be used in industry for automatic tagging or as part of internet search engines.

'Our basic approach is to take a large number of photos - we started with 60,000 photos - and to manually tag them with a variety of keywords that describe their contents,' said Jia Li, an associate professor of statistics at Penn State.

'We then teach the computer to recognise patterns in colour and texture among these photos and to assign our keywords to new photos that seem to contain similar content. Eventually, we hope to reverse the process so that a person can use the keywords to search the web for relevant images.'