Google Googles – photo recognition at scale

by SteveBayle on December 20, 2009

Today’s New York Times business section has a good overview article about Google Goggles, a photo recognition app in Google Labs: Snap and Search (No Words Needed).

Google says Goggles works best with certain categories of objects, including CDs, movie posters, products, wine labels, artwork, buildings and landmarks. It can read business cards and book covers. It doesn’t do so well with trees, cars or objects whose shape can change, like a towel. And it has trouble recognizing objects in less than ideal lighting conditions.

It’s not hard to imagine a slew of commercial applications for this technology. You could compare prices of a product online, learn how to operate that old water heater whose manual you have lost or find out about the environmental record of a certain brand of tuna.

Someday soon between bar code scanning and photo recognition technology like Google Goggles, shoppers will be able to get information about virtually any mass market product carried by retail stores. What they can do with that information is what will become important as these whizbang technologies become taken for granted elements of the mobile phone’s operating system, just as no one today thinks about how amazing it is that a PC word processing program can access hundreds if not thousands of type fonts, except for those senior citizens amongst us who go back to the days of the IBM Selectric and the amazing magic of changing type fonts by switching metal balls in the typewriter.

Share and Enjoy:
  • Twitter
  • Facebook
  • Print
  • Digg
  • Sphinn
  • Mixx
  • Google Bookmarks
  • Suggest to Techmeme via Twitter
  • Technorati
  • Tumblr

Leave a Comment

Powered by WP Hashcash

Previous post: Getting a recommendation for a commodity product

Next post: Wal-Mart has yet to discover self-service w/smartphones