rss
03-19-2014, 08:26 PM
With Facebook's New Tech, You'll Never Need to K**w Friends' Faces Again
http://rack.3.mshcdn.com/media/ZgkyMDE0LzAzLzE5L2M3L0ZhY2VfUmVjb2duLjljOWFmLmpwZw pwCXRodW1iCTU3NXgzMjMjCmUJanBn/34c11c91/39c/Face_Recognition_1.jpghttp://rack.3.mshcdn.com/assets/feed-tw-df3e816c4e85a109d6e247013aed8d66.jpg (http://twitter.com/share?via=Mashable&text=With+Facebook%27s+New+Tech%2C+You%27ll+Never+ Need+to+K**w+Friends%27+Faces+Again&src=http%3A%2F%2Fmashable.com%2F2014%2F03%2F19%2Ff acebook-facial-recognition-deepface%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_medium%3Dfeed%26utm_source%3Drss)htt p://rack.1.mshcdn.com/assets/feed-fb-fdab25e3700868c9621fb03b7fd07c38.jpg (http://www.facebook.com/sharer.php?u=http%3A%2F%2Fmashable.com%2F2014%2F03 %2F19%2Ffacebook-facial-recognition-deepface%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_medium%3Dfeed%26utm_source%3Drss&src=sp)
It's easy for humans to identify faces in pictures on Facebook (http://mashable.com/category/facebook/?utm_medium=feed&utm_source=rss), but the method isn't as simple for computers. Sure, Facebook has a suggested prompt that predicts who you're trying to tag, but **w the company is working on a tech**logy that promises "near-human accuracy" so you won't have to do it yourself in the future.
Facebook's API Group is developing software called DeepFace (https://www.facebook.com/publications/546316888800776/), which maps 3D facial features and creates a colorless model to narrow in on specific characterizations. The accuracy of the method is 97.25%, which is just under the 97.5% accuracy that a human can identify, according to the group. Read more... (http://mashable.com/2014/03/19/facebook-facial-recognition-deepface/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss)
More about Facebook (http://mashable.com/category/facebook/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), Facial Recognition (http://mashable.com/category/facial-recognition/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), Tech (http://mashable.com/tech/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), and Apps Software (http://mashable.com/apps-software/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss)http://ad.doubleclick.net/ad/mash.to/rss;pos=atf;tag=ad;mtype=standard;type=rss;sz=300x 250;ord=1395246197 (http://ad.doubleclick.net/jump/mash.to/rss;pos=atf;tag=ad;mtype=standard;type=rss;sz=300x 250;ord=1395246197)http://feeds.feedburner.com/~r/Mashable/~4/oZpPBplnWj4
http://rack.3.mshcdn.com/media/ZgkyMDE0LzAzLzE5L2M3L0ZhY2VfUmVjb2duLjljOWFmLmpwZw pwCXRodW1iCTU3NXgzMjMjCmUJanBn/34c11c91/39c/Face_Recognition_1.jpghttp://rack.3.mshcdn.com/assets/feed-tw-df3e816c4e85a109d6e247013aed8d66.jpg (http://twitter.com/share?via=Mashable&text=With+Facebook%27s+New+Tech%2C+You%27ll+Never+ Need+to+K**w+Friends%27+Faces+Again&src=http%3A%2F%2Fmashable.com%2F2014%2F03%2F19%2Ff acebook-facial-recognition-deepface%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_medium%3Dfeed%26utm_source%3Drss)htt p://rack.1.mshcdn.com/assets/feed-fb-fdab25e3700868c9621fb03b7fd07c38.jpg (http://www.facebook.com/sharer.php?u=http%3A%2F%2Fmashable.com%2F2014%2F03 %2F19%2Ffacebook-facial-recognition-deepface%2F%3Futm_campaign%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_cid%3DMash-Prod-RSS-Feedburner-All-Partial%26utm_medium%3Dfeed%26utm_source%3Drss&src=sp)
It's easy for humans to identify faces in pictures on Facebook (http://mashable.com/category/facebook/?utm_medium=feed&utm_source=rss), but the method isn't as simple for computers. Sure, Facebook has a suggested prompt that predicts who you're trying to tag, but **w the company is working on a tech**logy that promises "near-human accuracy" so you won't have to do it yourself in the future.
Facebook's API Group is developing software called DeepFace (https://www.facebook.com/publications/546316888800776/), which maps 3D facial features and creates a colorless model to narrow in on specific characterizations. The accuracy of the method is 97.25%, which is just under the 97.5% accuracy that a human can identify, according to the group. Read more... (http://mashable.com/2014/03/19/facebook-facial-recognition-deepface/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss)
More about Facebook (http://mashable.com/category/facebook/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), Facial Recognition (http://mashable.com/category/facial-recognition/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), Tech (http://mashable.com/tech/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss), and Apps Software (http://mashable.com/apps-software/?utm_campaign=Mash-Prod-RSS-Feedburner-All-Partial&utm_cid=Mash-Prod-RSS-Feedburner-All-Partial&utm_medium=feed&utm_source=rss)http://ad.doubleclick.net/ad/mash.to/rss;pos=atf;tag=ad;mtype=standard;type=rss;sz=300x 250;ord=1395246197 (http://ad.doubleclick.net/jump/mash.to/rss;pos=atf;tag=ad;mtype=standard;type=rss;sz=300x 250;ord=1395246197)http://feeds.feedburner.com/~r/Mashable/~4/oZpPBplnWj4