In Your Face I.D.

We've now reached a hi-tech point where computers can recognize us by our faces. Just like you can pick out people that you know in a crowd, a computer with a camera can now do the same thing. With just a mere glimpse of your face - you could be found and identified while you're walking on the street, driving your car, on the job or in a stadium filled with thousands of people.

You think about how we recognize each other-- It's by our faces. Now, computers can be programmed to do the same thing. If your facial image is on file, a computer with a camera could pick you out of a crowd. Police see it as a way to cut down crime and the state of Illinois is using this technology. But how far can this go when your I.D. is in your face?

Chances are you're not even aware of it. If you've renewed your Illinois driver's license recently, the photo session is about more than getting a new picture of yourself for your wallet. Your face is being stored.

In an array of computer servers in Springfield, your facial image is somewhere among 8 million others. And these computers are searching for your face to see if you really are who you say you are. "What it provides for us is pretty quick identification of persons who are the same person who pretend to be different persons," said Beth Langen, IL Sec. Of State's Office.

Illinois is among a handful of states now using facial recognition technology to stop driver's license fraud. It's nabbing hundreds of people already. It works by finding the visible landmarks on your face and then creating a mathematical computation, based upon those features, unique to you. Visage Technology, based outside of Boston, is one of the companies that has developed this. "Our cameras have to be able to catch both eyes. Once we capture that, we can analyze the face," said Gretchen Lewis, Visage Technology, Inc. This is the same company that was there at the super bowl in Tampa, capturing the faces of every fan that came to the game, looking for criminals in the crowd. That certainly raised some eyebrows.

"There's something repugnant about catching someone's digital image. I think this society's willing to take some risks to have anonymity," said John Roberts, ACLU Florida.

"I go into the 7-11, McDonald's, bank, gas station, I have my picture taken. Not only taken, but stored. With our technology, bouncing it against a database, if there's no match, it's being dropped immediately," said Tom Colatosti, Visage Technology, Inc.

It does create the possibility that you could be under surveillance with your facial image being captured and analyzed, simply as you walk down the street. It's not happening yet here in Chicago.

But it is happening in London, England. This is the borough of Newham in London's east end. It's an area that's had a relatively high crime rate in years past. But now, there are extra eyes watching what's going on here. The extra eyes are in the form of surveillance cameras. In some neighborhoods there are more than 300 cameras on poles, etc? So chances are, when you're walking on the streets of Newham: someone is watching you. Those doing the watching are local government employees and police officers. "What we have seen is an incredible drop-off of crime in the area," said Bob Lack, Newham emergency services director. That's not surprising, because it appears the cameras are everywhere: watching people on the sidewalks, on the streets, in the parking lots, in the lobbies of buildings, and even capturing the license plate numbers of cars passing by.

"To stop crime, so they can surveillance people, catch people doing things they shouldn't be doing," said Charlene Whitehorne, resident of Newham. And the police are getting a "heads-up" on crime, because the cameras and computers can pick the faces of known criminals out of the crowds. "They are targeting a very small minority of people who are responsible for a large amount of crime in the area," said Tim Pidgeon, Visionics Inc. "You don't think: everywhere I go someone's watching, but it's nice to know if something did happen here they'd be caught," said Jane Harvey, resident. And it's catching on in the United States.

A number of casinos, including some in the Chicago area, are using security cameras and this 'face-grabbing' technology to watch out for cheaters and track them if they return. The immigration and naturalization service has tested a similar system that it could use for passport control or border control, but it's put future plans for the technology on hold for now.

But down in Tampa, Florida, they are talking about using it in their nightclub area called your city. This is an area already blanketed by many security cameras. If computerized facial recognition is added, anyone with a criminal record simply out on the streets - could be a marked man. "If you haven't committed a crime, and you're not intent on committing a crime, you don't have a problem," said Bob Buckhorn, Tampa city councilman. "One could make the same argument in response to a search of someone's home without a warrant," said Colleen Connell, ACLU Illinois.

It's the worries about Big Brother that have civil libertarians saying that the guidelines and laws need to be set now, before this technology moves into many areas of our lives. You could buy products, do your banking, and enter your home merely by showing your face to a camera. But if all those activities are being tracked and monitored by someone, where can you find privacy?

Applications of Face Recognition Systems

Face recognition systems are no longer limited to identity verification and surveillance tasks. Growing numbers of applications are starting to use face-recognition as the initial step towards interpreting human actions, intention, and behavior, as a central part of next-generation smart environments. Many of the actions and behaviors humans display can only be interpreted if you also know the person's identity, and the identity of the people around them. Examples are a valued repeat customer entering a store, or behavior monitoring in an eldercare or childcare facility, and command-and-control interfaces in a military or industrial setting. In each of these applications identity information is crucial in order to provide machines with the background knowledge needed to interpret measurements and observations of human actions.

Face Recognition for Smart Environments

Researchers today are actively building smart environments (i.e. visual, audio, and haptic interfaces to environments such as rooms, cars, and office desks). In these applications a key goal is usually to give machines perceptual abilities that allow them to function naturally with people -- to recognize the people and remember their preferences and peculiarities, to know what they are looking at, and to interpret their words, gestures, and unconscious cues such as vocal prosody and body language. Researchers are using these perceptually-aware devices to explore applications in health care, entertainment, and collaborative work. Recognition of facial expression is an important example of how face recognition interacts with other smart environment capabilities. It is important that a smart system knows whether the user looks impatient because information is being presented too slowly, or confused because it is going too fast -- facial expressions provide cues for identifying and distinguishing between these different states. In recent years much effort has been put into the area of recognizing facial expression, a capability that is critical for a variety of human-machine interfaces, with the hope of creating a person-independent expression recognition capability. While there are indeed similarities in expressions across cultures and across people, for anything but the most gross facial expressions analysis must be done relative to the person's normal facial rest state -- something that definitely isn't the same across people. Consequently, facial expression research has so far been limited to recognition of a few discrete expressions rather than addressing the entire spectrum of expression along with its subtle variations. Before one can achieve a really useful expression analysis capability one must be able to first recognize the person, and tune the parameters of the system to that specific person.

Wearable Recognition Systems

When we build computers, cameras, microphones and other sensors into a person's clothes, the computer's view moves from a passive third-person to an active first-person vantage point . These wearable devices are able to adapt to a specific user and to be more intimately and actively involved in the user's activities. The field of wearable computing is rapidly expanding, and just recently became a full-fledged Technical Committee within the IEEE Computer Society. Consequently, we can expect to see rapidly-growing interest in the largely-unexplored area of first-person image interpretation. Face recognition is an integral part of wearable systems like memory aides, remembrance agents, and context-aware systems. Thus there is a need for many future recognition systems to be integrated with the user's clothing and accessories. For instance, if you build a camera into your eyeglasses, then face recognition software can help you remember the name of the person you are looking at by whispering their name in your ear. Such devices are beginning to be tested by the US Army for use by border guards in Bosnia, and by researchers at the University of Rochester's Center for Future Health for use by Alzheimer's patients.

Conclusion

Face recognition technology has come a long way in the last twenty years. Today, machines are able to automatically verify identity information for secure transactions, for surveillance and security tasks, and for access control to buildings etc. These applications usually work in controlled environments and recognition algorithms can take advantage of the environmental constraints to obtain high recognition accuracy. However, next generation face recognition systems are going to have widespread application in smart environments -- where computers and machines are more like helpful assistants. To achieve this goal computers must be able to reliably identify nearby people in a manner that fits naturally within the pattern of normal human interactions. They must not require special interactions and must conform to human intuitions about when recognition is likely. This implies that future smart environments should use the same modalities as humans, and have approximately the same limitations. These goals now appear in reach -- however, substantial research remains to be done in making person recognition technology work reliably, in widely varying conditions using information from single or multiple modalities.