Thursday, May 31, 2007
Google Adds Facial Recognition to Image Search
It looks like Google's 2006 acquisition of Neven Vision, a company specializing in facial recognition software, is finally starting to pay off. Google Blogoscoped, a blog dedicated to everything related to Google, got a tip from a Google engineer that Google had secretly added some facial recognition abilities to its image search this week.
The feature remains unofficial and unannounced, but you can add a small query string to the end of your Google Image search URL to see the facial recognition software in action.
For example, do a normal Google image search for "Starbuck Battlestar" and your image results should produce images from the American SciFi TV show Battlestar Galactica. Then try adding "&imgtype=face" to the end of the URL. Your new search results will only contain photos of people and tight shots of their faces. Cool right?

Last August, Google Picasa product manager Adrian Graham had this to say about Google's acquisition of Neven Vision in the official Google blog:
BeSocial: flickr | digg story | methodshop

For example, do a normal Google image search for "Starbuck Battlestar" and your image results should produce images from the American SciFi TV show Battlestar Galactica. Then try adding "&imgtype=face" to the end of the URL. Your new search results will only contain photos of people and tight shots of their faces. Cool right?

Last August, Google Picasa product manager Adrian Graham had this to say about Google's acquisition of Neven Vision in the official Google blog:
"Neven Vision comes to Google with deep technology and expertise around automatically extracting information from a photo. It could be as simple as detecting whether or not a photo contains a person, or, one day, as complex as recognizing people, places, and objects."
BeSocial: flickr | digg story | methodshop
Labels: tech news
Subscribe to Posts [Atom]