Google takes OCR to new level

Imagine an image of a typical urban street scene. That image may contain street signs, store names, restaurant menus, opening hours and perhaps even address numbers. Now imagine a computer program that could recognise and extract text from that image, or a video of the scene, and how that could progress the world of search online.

This sort of technology may not be far off. A patent application titled “Recognizing Text in Images”, lodged by Google in the middle of last year and recently published, appears to take optical character recognition (OCR) to a new level. Not only would it enable keywords to be extracted from images but also be able to match images with keywords.

TechCrunch’s Duncan Riley writes, “I may be stating the blatantly obvious when I say that if Google has found a way to index text in static images and video this is a great leap forward in the progression of search technology. This will make every book in the Google Books database really searchable, with the next step being YouTube, Flickr (or Picasa Web) and more. The search capabilities of the future just became seriously advanced.”

Meanwhile, Google isn't giving anything away. "We file patent applications on a variety of ideas that our employees come up with," said a company spokesperson. "Some of those ideas later mature into real products or services, some don't. Prospective product announcements should not necessarily be inferred from our patent applications."

Tags: Google, image search, keywords, OCR, optical character recognition, search marketing