Google has filed for image text patent

The application, made in June 2007, was published on Thursday and covers "methods, systems and apparatus including computer program products for using extracted image text," according to Google.
"In one implementation, a computer-implemented method is provided," reads the abstract for the application. "The method includes receiving an input of one or more image-search terms and identifying keywords from the received one or more image search terms. The method also includes searching a collection of keywords including keywords extracted from image text, retrieving an image associated with extracted image text corresponding to one or more of the image-search terms, and presenting the image."
Google, which is already the proprietor of not only the most widely used image search facility on the Internet but also the leading video site, YouTube, has much to gain from being able to correctly interpret text held within images and video. Such a capability could, for example, be used to create more accurate keywords or for the automatic tagging of files and the identification of where a picture was taken based on signage in the background.

Source