Google has done some interesting things with mobile search in the past year, introducing voice search and local search using the location awareness capabilities of today’s smartphones. Today, they are introducing visual search called Google Goggles.
Google Goggles let’s you take a picture of something, and Google will do a quick search that tells you more whatever you were looking at. Obviously, it won’t work for everything, but it does have fairly broad application. They provide examples of how you can use it for looking up information about a landmark, artwork, bottle of wine, brand, book, contact info (i.e. a business card) or place.
How Google Goggles Works
In a nutshell, Goggles lets users search for objects using images rather than words. Simply take a picture with your phone’s camera, and if we recognize the item, Goggles returns relevant search results. Right now Goggles identifies landmarks, works of art, and products (among other things), and in all cases its ability to “see further” is rooted in powerful computing, pervasive connectivity, and the cloud:
- First they send the user’s image to Google’s datacenters
- Next they create signatures of objects in the image using computer vision algorithms
- They then compare signatures against all other known items in our image recognition databases; and
- They figure out how many matches exist; and
- Return one or more search results, based on available meta data and ranking signals; and
- Google does all of this in just a few seconds
Google Goggles Explained
This video provides a great introduction to Google Goggles.
It’s a clever idea, but it’s currently only available on phones running Android 1.6+. Of course there’s no reason they couldn’t do the same for the iPhone or other smartphones, and I suspect versions for those will pop up soon.
If you’re running an Android phone, head over to the Android Market on your phone and search for “Google Goggles.” Let us know how it works for you!