Posts Tagged ‘facedetection’

9 Features Every DSLR Should Have Now

dslrcut

They say that the DSLR’s better days are behind it, but it’s still the choice for most working pros. Rapid advances on point and shoots, ILCs (mirrorless interchangeable lens cameras) and smart phones have left the DSLR looking like the camera of yesteryear, so here are a few features we think every DSLR should have now. Read more…

Using a Face Detector to Generate Creepy Mugs from Random Polygons

The man in the moon and the face on mars. These are both the result of a psychological phenomenon known as pareidolia, which involves the brain trying to perceive random signals as significant. It’s one of the brain’s face detection mechanisms, and causes us to see faces where they don’t actually exist — the Virgin Mary’s face on toast, for example.

Programmer Phil McCarthy decided to play around with the idea of paredoila in artificial intelligence, and created a program called pareidoloop. It uses face detection algorithms to “see” human faces in randomly generated polygons.
Read more…

Apple to Use Face Detection for Exposure Metering and Snappy Autofocus

Apple camera patent for face detection exposure metering

Face detection has become the snapshot photographer’s invaluable assistant in ensuring tack-sharp faces, but soon it’ll be able to add two more job responsibilities to its resume: exposure metering and speedier autofocus. Two patents recently awarded to Apple show that future iOS cameras (perhaps the next iPhone?) will have standard camera features that rely much more on face detection technology. The first patent, titled “Dynamic exposure metering based on face detection“, allows the camera to automatically select faces as the primary target for metering. In more difficult situations — group shots or people standing in front of a crowd, for example — the camera will use factors such as “head proximity” to select the primary subject.
Read more…

Canon Face Recognition Feature Gives Friends Preferential Treatment

Canon’s latest compact cameras at CES this year have some fancy new facial recognition features that assist in portrait shots. Up to 12 people can be stored in the camera. Simply snap a photo of your friends face, provide the friend’s name (and birthday if you wish), and the camera will recognize your friend from that point forward. In group shots, the camera will give your friends’ faces preferential treatment, making sure that they’re properly in focus and exposed.
Read more…

Face Swap App Lets You Quickly Swap Faces With Friends

It looks like Microsoft is finally putting its war chest and brilliant minds to good use: the company has released a new free app for Windows Phone users called Face Swap. The app uses face detection to let you quickly switch the faces of subjects in your photos. Simply shake the phone and faces will be swapped! The resulting face swap photos can be saved or shared on social networking websites. Hopefully they turn this into a web app soon.

Face Swap (via Engadget)

Apesnake: A Photobooth Triggered by Facial Expressions

The Apesnake Photobooth is a novel photobooth triggered by facial expressions. Created by Che-Wei Wang & David Penuela, it detects the eyes and mouth of the subject and triggers the shutter on a Canon 1000D when they’re found to match a desired expression (they chose the Manwolf face). The booth also automatically uploads photographs to a dedicated Facebook page.
Read more…

Facial Recognition with the iPhone May Lead to Pretty Creepy Apps

Last year, Apple purchased Swedish facial recognition firm Polar Rose for $22 million, and yesterday’s iPhone 4S announcement revealed that the technology is now baked into iOS and is touted as one of big new camera features. The iPhone is now a compact camera and mobile computer that can detect — and possibly recognize — faces.
Read more…

Facial Recognition May Get Really Creepy Really Soon

Facial recognition features are appearing in everything from cameras to photo-sharing sites, but have you thought about the different security and privacy concerns it introduces? Fast Company has published a piece on how mobile apps in the future may be able to quickly look up your identity, your personal information, and perhaps even your social security number!

[CMU researchers] used three relatively simple technologies to create their face recognition system: An off-the-shelf face recognizer, cloud computing processing, and personal data available through the public feed at social networking sites such as Facebook […] Combining the data gathered from the face recognizer hardware with clever search algorithms that were processed on a cloud-computing platform, the team has performed three powerful experiments: They were able to “unmask” people on a popular dating site where it’s common to protect real identities using pseudonyms, and they ID’d students walking in public on campus by grabbing their profile photos from Facebook.

Most impressively the research algorithm tried to predict personal interests and even to deduce the social security number of CMU students based solely on an image of their face–by interrogating deeper into information that’s freely available online.

You might want to invest in a pair of censorship sunglasses after all!

Your Face Is Your Key [Fast Company]


Image credit: Face Detection Example (Bogdan and Anne) by mr. ‘sto

Facebook Adding Face Detection to Its Photos App

Looks like Facebook’s recent acquisition of Divvyshot was not for naught.

In a post on the Facebook blog yesterday, Divvyshot founder Sam Odio announced that Facebook is adding the same face detection features found in many consumer cameras to its uber-popular Facebook Photos app.

Previously, users had to manually select each face found in a photograph to tag it with a friend’s name, but now the service will automatically select each face and prompt you for the name, streamlining the process and making it much easier for uploaders.

I’m guessing we’ll soon see features added that promote collaboration and pooling together photographs as a group to a shared pool, similar to what Divvyshot offered prior to the acquisition and shutdown.