Using face recognition to cast Madison the Movie
Post by Jesse Russell on 1/16/2006 1:05pm
This weekend Sara on Working for the Weekend shared her experience using face recognition technology on MyHeritage.com to find out the celebrity she resembles most is Hillary Clinton. The genealogy website is using the celebrity matching gimmick as a promotional tool in preparation for launching the technology to help build family trees. Hypothetically, your face should match up with others in your family line. The site explains how it works:
Recognizing faces is done by algorithms that compare the faces in your photo, with all faces previously known to MyHeritage Face Recognition, through photos and meta-data contributed by yourself and other users. So the more photos added to the system, the more powerful it becomes. If people in your photos are not recognized well, it is likely that MyHeritage.com has never encountered them before. By adding these photos to MyHeritage.com and annotating the people in the photo manually, MyHeritage.com will "learn" these faces and will be able to recognize them in future photos, even in different ages of the same person's life.
While the celebrity matching has mixed results, Dane101 thought it would be fun to randomly select some local public figures and throw them in the kettle. For example, we found that Mayor Dave Cieslewicz has a facial structure that closely matches Monty Python actor John Cleese. Another close match for the mayor was X-Files star David Duchovny. For more matches, click Ã¢â‚¬Å“read more.Ã¢â‚¬Â
Sandra Bullock, Leonard Nimoy, Barry Gibb, Kim Bassinger, Dan Quayle, Andy Warhol, Coleman Hawkins, Diane Keaton, Scarlett Johansen, Matthew Perry, John Cusack, Nicholas Cage, Cameron Diaz
Jesse was born and raised in Connecticut, began blogging in 1997, and moved to Madison in 2003. In 2005, he co-founded dane101 along with Kristian Knutson and Shane Wealti. In addition to helping nearly a dozen contributors run this website he's helped launch various events in the city including What's Your Damage?!, the MadPubQuiz of Awesomeness, the Fire Ball Masquerade, Dane101's Freakin' Halloweekend, and more.