"Images are universal but image search is not," said University of Washington Professor Oren Etzioni, who led the research. "A person who types his or her search in English won't find images tagged in Chinese and a Dutch person won't find images tagged in English. We've created a collaborative tool that solves this problem."
Search engines such as Google look for images by detecting the search term in captions and text. But since the process looks for a string of letters, the results are limited to the seeker's language.
The new PanImages technology automatically translates the search term into about 300 languages.
"We want to serve the vast number of people who don't speak one of the major languages," Etzioni said. "As the Internet becomes more widely available … it becomes increasingly important to serve people who don't speak English, French or Chinese."
The new multilingual search tool developed at the University of Washington's Turing Center was presented in Denmark this week during the Machine Translation Summit meeting.
Toddler uninjured after being knocked over by Obama family dog
Texas principal bans speaking Spanish, stirs controversy