Wednesday, November 21, 2012

FaceFirst's biometric software can use a database of photos to identify you in public.

The installation of high resolution cameras should worry everyone, it's only a matter of time before they are everywhere and every movement we make will be tracked.

Fire a gun and your location can be pinpointed, your face photographed and your identity instantly determined -- all thanks to a new technology tag team.

When Safety Dynamics’ acoustic sensors detect a gunshot, they zero in on the shooter’s location and point a high-resolution camera at his or her face. Airborne Biometrics Group’s FaceFirst software then runs the shooter’s image against a biometric database to determine identity, even creating a new record if it can’t find one.

The companies say this is the world’s first such detector to instantly ID a shooter, and aim to make it available to law enforcement agencies and private physical security firms.

"Facial recognition is a technology that captures individual faces in real time – in photos or video – and give precise identification based on database photographs and to do this, they provide service facial recognition software which is known as FaceFirst. This allows you to identify individuals with prior arrest records, suspected shoplifters and persons of interest on the internal watch/ban lists."

FaceFirst Specifics: 

It provides an affordable way to reduce crime as it has real-time, government-grade facial identification technology which instantly matches with a huge central database thereby providing an alert in seconds so the crime can be stopped before it happens.

It is the only complete, turnkey facial recognition service available today.

It uses the world’s most highly developed facial recognition software and support is available seven days a week during business hours. If there are special requirement, you can contact us.

You can select your own facial databases and add or delete individual records at will.

You can also choose your delivery system whether it be e-mail, SMS (Short Message Service), MMS (Multimedia Messaging Service), cash register alerts or log-only and they provide the complete installation service.

They have a massive, centrally-managed database and server farm at their headquarters which allows us to provide you with state-of-the-art technology for much, much less than other facial recognition firms.
  • Provides automated alerts in real time to cell phones, PDA’s (Personal Digital Assistant), computers, cash registers. 
  • Utilizes your filed-and-forgotten lists of persons of interest.
  • Customized database access – your watch list, lists from other participating companies and public databases you choose.
  • FaceFirst operator center allows your operators to optionally verify identifications when an automated match is not possible.
  • Affordable for all applications, because the heart of the system is managed off-site.
  • No technical jargon to learn, no need for time-consuming training.
  • Easy to integrate with existing security systems.
  • Inconspicuous camera.
  • Doesn’t affect normal traffic patterns.
  • Lightning fast – up to 1 million facial comparisons per second.
  • Operates up to 100 feet from subject.

Gun-shot detection and facial recognition technologies have proliferated in recent years: Safety Dynamics competes with other solutions for threat recognition and localization such as Shotspotter, which relies on wide-area acoustic surveillance and GPS technology to triangulate the source of gunshots.

It goes a step further by adding facial recognition, an area in biometrics that has made huge progress in the past decade. Today’s systems often exploit 3D algorithms to boost accuracy, for example.

The company says the successful identification rate has improved from approximately 75 percent ten years ago to better than 95 percent by 2006 in government-sponsored tests. In tests run by the National Institute of Standards and Technology, its technology was given top ranking.

Companies are also discouraged from identifying people where they would not want to be identified and give a bathroom or locker room as an example.

Software that identifies facial images such as an “app that allows users to identify strangers in public places, such as on the street or in a bar” is also discouraged by the FTC.

They are also encouraged to ensure the facial images are secure, notify people their faces are being captured and retained and obtain express permission for using the image.

Facial recognition technology has the potential to both better protect civilians and their privacy as well as invade it.

FaceFirst (Video) demo:

Police are testing a hand-held version of FaceFirst.

San Diego, CA - A groundbreaking new facial recognition system is being tested in San Diego. It can identify faces in a split second.

"We believe facial recognition will be in every day society," said San Diego native Joseph Saad.
Saad is the business development director for FaceFirst, the Camarilo, Calif. based company that has become the first to develop software that makes facial recognition almost instantaneous. Right now, there are limitations to facial recognition systems. Once cameras spot a person, it could take some five minutes to make a match. By that time, the person could be long gone.

Those concerns have limited facial recognition to places like airports and casinos, until now.

Using unique algorithms, FaceFirst can compare millions of photos per second, which can lead to a match in one second.

10News has learned an unnamed law enforcement agency in San Diego County has been testing a handheld version for about five months.

"If they spot someone who doesn't have identification, they can take their picture with their phone and immediately get a result," said Saad.

10News was told the software has led to several local arrests.

FaceFirst is now looking to expand beyond law enforcement into the military and retail, where photos of shoplifters can be stored and would-be criminals spotted the moment they enter into a store simply by showing their face.

The San Diego chapter of the American Civil Liberties Union tells 10News, "Americans should be able to move about and not live under the constant watchful camera lens like characters in a George Orwell novel."

In response, FaceFirst points out that databases used for face matches usually are filled with criminals and suspects.

Facial recognition software can now reveal almost everything about us.

Carnegie Mellon University researcher Alessandro Acquisti says that he has proven that most people can be identified through one photograph.
Acquisti found that the convergence of facial recognition software with social networks like Facebook tilt those odds wildly in favor of the would-be exposer, or stalker.
Acquisti searched for dating site users within 50 miles of a zip code, found about 6,000, and then found 110,000 Facebook profiles where users said they lived near that same zip code. After eliminating some profiles that didn’t match his criteria, he instructed computers to churn through about 500 million pairs of possibilities.
It would take a human about 2 million hours to compete such a task, but Carnegie Mellon’s cloud computing cluster got results in about 15 hours. One in 10 members of the dating site were positively “outed” by the database search. A bit of fine-tuning — limiting the geographic area further or allowing approximate matches — produced even better results. And one sobering reminder: The researchers didn’t even need to log in to Facebook to get these results.
Acquisti’s team enjoyed even better results when they could obtain photographs themselves for matching purposes. Random students who agreed to be photographed on the Pittsburgh campus of Carnegie Mellon could be positively identified at three times the initial rate — or more than 30 percent.
The researchers didn’t stop there. Next, they linked the photos and names to student likes and dislikes gleaned from their profiles, with about 75 percent accuracy. Then, they combined this effort with work Acquisti had done in 2009 on predicting Social Security numbers, and found that they could predict the Social Security number for 28 percent of the subjects within four guesses. Finally, they built a mobile phone application that could achieve the same results while wandering around campus.

Store mannequins that spy on consumers.

Mannequins in fashion boutiques are now being fitted with secret cameras to 'spy' on shoppers' buying habits.

Benetton is among the High Street fashion chains to have deployed the dummies equipped with technology adapted from security systems used to identify criminals at airports.

From the outside, the $5,072 EyeSee dummy looks like any other mannequin, but behind its blank gaze it hides a camera feeding images into facial recognition software that logs the age, gender and race of shoppers.

This information is fed into a computer and is 'aggregated' to offer retailers using the system statistical and contextual information they can use to develop their marketing strategies.

The EyeSee looks ordinary enough on the outside, with its slender polystyrene frame, blank face and improbable pose. Inside, it’s no dummy. A camera embedded in one eye feeds data into facial-recognition software like that used by police. It logs the age, gender, and race of passers-by.

Demand for the device shows how retailers are turning to technology to help personalize their offers as growth slows in the $245 billion luxury goods industry. Bain & Co. predicts the luxury market will expand 5 percent in 2012, less than half last year’s rate.

“Any software that can help profile people while keeping their identities anonymous is fantastic,” said Uché Okonkwo, executive director of consultant Luxe Corp. It “could really enhance the shopping experience, the product assortment, and help brands better understand their customers.”

The mannequin, which went on sale last December and is now being used in three European countries and the U.S., has led one outlet to adjust its window displays after revealing that men who shopped in the first two days of a sale spent more than women, according to Almax.

A spokesman for Benetton declined to elaborate on where or why the clothier is using the EyeSee.

Max Catanese, chief executive officer of the 40-year-old mannequin maker, declined to name clients, citing confidentiality agreements. Five companies, including leading fashion brands, are using a total of “a few dozen” of the mannequins with orders for at least that many more, he says.

Burberry Group Plc (BRBY) and Nordstrom Inc. (JWN) are among retailers that say they aren’t on the list. Even so, they are helping blur the line between the physical shopping experience and Web retailing by setting up WiFi, iPads and video screens at their outlets to better engage shoppers. 

Nordstrom, a U.S. chain of more than 100 department stores, says facial-recognition software may go a step too far.

Others say profiling customers raises legal and ethical issues. U.S. and European Union regulations permit the use of cameras for security purposes, though retailers need to put up signs in their stores warning customers they may be filmed. Watching people solely for commercial gain may break the rules and could be viewed as gathering personal data without consent, says Christopher Mesnooh, a partner at law firm Field Fisher Waterhouse in Paris.

How can you protect your privacy from surveillance cameras?

First, you need to understand how the technology works. There are certain points on the face that are targeted by the software: particularly eyes, nose, and mouth; where they meet, and the distance between them. The trick is to obscure these points without drawing undue attention to yourself through your efforts to camouflage them.

Black geometric shapes painted on the face seem to “fool” the devices into not recognizing the photo as a human face. However, it isn’t exactly subtle to walk around with black triangles and squares painted randomly on one’s face. One researcher from NYU, Adam Harvey, has been working on reverse engineering the technology in order to protect privacy. In the photo below, the faces with the red squares around them were identifiable by the software.

The places you want to obscure are:
  • Distance between the eyes
  • Width of the nose
  • Depth of the eye sockets
  • The shape of the cheekbones
  • The length of the jaw line
“A spike of hair proved to be effective if it covered the area where the eyes, forehead and nose come together. Computer-vision software often looks for that spot, said Harvey, and will not detect a face without it. “(source)

Hats, hoodies and big sunglasses can help obscure some of the targeted facial areas but can also make you look suspicious, especially if the weather conditions don’t support the wearing of those items.

If you are identified, take steps to limit the amount of information that is available about you.
  • Limit your use of photographs on photosharing websites like Picasa and Photobucket.
  • Don’t provide personal information about yourself and your family on social media sites like Facebook.
  • Check your privacy settings on Facebook to be sure that others cannot “tag” you in photographs.
  • Don’t use a photograph of yourself as a profile picture on Facebook – use a pet, a cup of coffee or something unidentifiable. Profile pictures cannot be made private.
  • Resist the urge to have your work place, your Alma Mater, and your family members linked to your Facebook profile.
  • Do some Google searches of yourself and see what information comes up. Take steps to remove as much information as possible.

No comments: