Google News

Google to Teach Robots to Read

Patent granted for "Recognizing Text in Images"

By Vlad Constandes, SEO News Editor

5th of January 2008, 01:11 GMT

Adjust text size:

There can be no doubt about it, technology has began moving at the speed of light, while humanity is trying to keep its pace. Yes, I know that the very same humans are to "blame" for the pace at which things are going, but it's a delicate topic, one that has too long been debated by religious groups and science communities, to name just two. A hundred years ago, we couldn't even take off for a certain flight that wouldn't end in a plane wreck and, now, we're entrusting our lives into the hands of the autopilot, to stay in the same context.

Google has played a very important part in the evolution of Internet with its programs,

applications and, most importantly, with its search engine and the way it works. It's helping as we speak, it hires people just for the purpose of continuous development of new ideas, and despite the fact that it's starting to look like a monopolistic squid, it's one of the biggest contributors to the state things are right now in the online world.

Last June, the Mountain View based company had a patent filed with the World Intellectual Property Organization for "Recognizing Text in Images" and it was granted yesterday. The patent would allow tasks like searching videos by keywords appearing in the content, as Informationweek.com noted.

Its abstract says that "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" and that "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." To be honest, I don't see it coming out too early for the average Internet savvy's use, but you can never know, especially when Google is involved.

I only wonder what level of detail would be needed at first for the robot that does the reading to be able to recognize it without any problem. I doubt that searching through a video that has a lower resolution, filmed with a phone (the type of clip that YouTube so generously hosts) would produce many results. Don't ask me why, it's a hunch. Or, what about the angle of the writing, would that be a problem?

TAGS:

google | text | recognition | robots | patent

SEARCH THE NEWS ARCHIVE :

Today's News | Yesterday's News | News Archive

User opinions:

No user comments yet.

Be the first to express your opinion using the form below!

Share your opinion:

SUBMIT PROGRAM \| ADVERTISE \| GET HELP \| SEND US FEEDBACK \| RSS FEEDS \| ENTER NEWS SITE \| ENGLISH BOARD \| ROMANIAN FORUM
© 2001 - 2008 Softpedia. All rights reserved. Softpedia™ and the Softpedia™ logo are registered trademarks of SoftNews NET SRL.	Copyright Information \| Privacy Policy \| Terms of Use \| Update your software \| Archive

NEWS CATEGORIES: