Infrastructure // PC & Servers
News
2/11/2011
07:30 PM
Connect Directly
LinkedIn
Twitter
Google+
RSS
E-Mail
50%
50%

Google Seeks Social Networking Face Recognition Patent

A capability withheld from Google Goggles could be improved by leveraging social data.

In December 2009, when Google introduced Google Goggles, VP of engineering Vic Gundotra said that while the image recognition software could identify faces, the company had decided to delay implementing facial recognition to consider the privacy implications.

But Google continues to develop such technology and is exploring its potential as a search tool amid a broad effort to enhance its services with social networking capabilities.

A patent application filed in Europe last August and published on February 10, 2011, "Facial Recognition With Social Network Aiding," describes how the availability of social networking profile data can increase the accuracy of facial recognition.

The listed inventors, David Petrou, Andrew Rabinovich, and Adam Hartwig, have all worked on Google Goggles.

Coincidentally, the filing took place about a week before Google announced its acquisition of visual search engine Like.com.

The technique described in the patent application envisions checking visual queries against images accessible through social networking applications, calendar applications, and collaborative applications. Images obtained from these applications can then be compared for similarity to create a ranked list of possible identities to be used in conjunction with other search-related data.

Google's engineers have given some thought as to how to implement such technology while respecting user privacy. The patent application describes a scenario in which facial recognition capabilities might be made available only to the person positively identified in a picture. It also describes a permission-based scenario: "[O]nce the person is positively identified, a request is sent to that person asking [if he or she] will allow the image to be returned [as] a result for future queries for people within [his or her] social network."

The ideal of mining social network data to improve facial recognition is not Google's alone. Researchers at Harvard published a paper on this topic, "Autotagging Facebook: Social Network Context Improves Photo Annotation," in 2008.

Google did not immediately respond to a request for comment.

In general, patents and patent applications are not necessarily indicative of future products. But this particular one makes it clear that search is going social and is looking to input beyond text.

Comment  | 
Print  | 
More Insights
Server Market Splitsville
Server Market Splitsville
Just because the server market's in the doldrums doesn't mean innovation has ceased. Far from it -- server technology is enjoying the biggest renaissance since the dawn of x86 systems. But the primary driver is now service providers, not enterprises.
Register for InformationWeek Newsletters
White Papers
Current Issue
InformationWeek Tech Digest - August 27, 2014
Who wins in cloud price wars? Short answer: not IT. Enterprises don't want bare-bones IaaS. Providers must focus on support, not undercutting rivals.
Flash Poll
Video
Slideshows
Twitter Feed
InformationWeek Radio
Archived InformationWeek Radio
Howard Marks talks about steps to take in choosing the right cloud storage solutions for your IT problems
Sponsored Live Streaming Video
Everything You've Been Told About Mobility Is Wrong
Attend this video symposium with Sean Wisdom, Global Director of Mobility Solutions, and learn about how you can harness powerful new products to mobilize your business potential.