Posts Tagged ‘facialrecognition’

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

US Gov Working on Geotagging Photos Using Only the Background

Facial recognition technology has become ubiquitous in recent years, being found in everything from the latest compact camera to websites like Facebook. The same may soon be said about location recognition. Through a new project called “Finder“, the US government military research division IARPA is looking into how to quickly and automatically identify where a photograph was taken without any geotag data. The goal is to use only the identifying features found in the background of scenes to determine the location — kinda like facial recognition except for landscapes.

(via Wired via PopPhoto)


Image credit: 090920-A-2794B-004 by isafmedia

Police in the US to Turn iPhone Cameras Back on Citizens

If ordinary citizens have the right to photograph police in public places, what about the other way around? That’s a question that’s sure to be asked often in the coming days, as 40 law enforcement agencies across the US are planning to use iPhones to photograph civilians for the purpose of identifying wanted perps. The system, called Mobile Offender Recognition and Information System (MORIS), costs $3,000 apiece and will be able to do facial recognition searches on a database of known criminals. Photographers’ rights will apply to cops too — police won’t be required to ask permission before snapping a photograph of your face!

(via Amateur Photographer and WSJ)

Facebook Adds Facial Recognition to Photo Tagging

Tagging friends in massive group photographs is about to get a whole lot easier. Facebook has just announced “tag suggestions”, which uses facial recognition technology to automatically group together photographs that have the same face in them.

Because photos are such an important part of Facebook, we want to be sure you know exactly how tag suggestions work: When you or a friend upload new photos, we use face recognition software—similar to that found in many photo editing tools—to match your new photos to other photos you’re tagged in. We group similar photos together and, whenever possible, suggest the name of the friend in the photos. [#]

While many people will probably opt for the old fashioned tagging method to have more control over the process, this feature will undoubtedly save many users a good deal of time. The feature will begin rolling out to users in the US over the next few weeks.

Face.com Launches Facial Recognition API

Here’s some nerdy news: Israeli facial recognition startup Face.com has just opened up its API, allowing developers to integrate its facial recognition technology in third-party websites and applications. Since launching a year ago, the company has scanned more than 7 billion photos and tagged more than 52 million faces through its Photo Finder and Photo Tagger applications on Facebook.

Now, the technology is no longer limited to Facebook, as any third-party developer can integrate facial recognition into their own apps. The API uses a REST-like interface similar to Twitter’s API, and takes in URLs to photos.

I’m interested in seeing what kind of creative applications developers can come up with. They’ve post a few example apps already using the API, and there’s talk of upcoming facial recognition augmented reality apps.

Facial Recognition for Dogs and Cats

If you’ve ever tried photographing a dog or cat, you probably know how difficult it can be to take a sharp photo while it’s looking at you. My friend’s dog (a pomeranian) is actually scared of my camera, and shies away when the DSLR is pointed at him.

FujiFilm’s new Finepix Z700 aims to make pet photographs easier by being the first camera to offer facial recognition for dogs and cats, and can automatically snap photographs for you when the pet is looking at the camera.

However, the technology is still pretty young, and has a ways to go before it rivals human facial recognition, which itself is ocassionally buggy.

For example, the camera has difficulty detecting pets that don’t stay still, and though it can detect up to 10 pet faces at once, it can’t handle a mix of dogs and cats. The subjects need to be either all dogs, or all cats.

Furthermore, some breeds of dogs (and maybe cats too?) can have pretty strange looking faces. The camera can’t handle those. FujiFilm even has a dedicated webpage listing the breeds of dogs and cats that the feature can usually detect, and includes sample images:

As you can see, you need to have a fairly… generic looking dog or cat if you want to detect its face.

Pets that cannot be easily detected include those that have: dark patches around the eyes or nose, too dark of a color, wrinkled/long/thin faces, or hair covering the eyes.

We’re guessing something like this will stump the camera:

Perhaps we should have titled this post, “Facial Recognition for Cute and Generic Looking Dogs and Cats”.

(via PC World)


Image credit: Castle Combe by Karen Roe