When an Illinois driver gets his or her photo taken at a Department of Motor Vehicles (DMV), the picture is sent to an enormous database and compared to other photos to find potential identity fraud.
The Illinois DMV's biometric-based facial recognition technology is part of a growing trend that has spread to approximately 20 states. Biometrics is the study of methods for recognizing individuals based on one or more physical or behavioral traits.
Illinois has been a leader in facial recognition programs at DMVs. It was among the first in the country to adopt such a program and has become a model for other states. The Illinois program has been a huge success, finding more than 5,000 cases of identity fraud from 1997 to 2007. Of the cases, 4,600 involved people with one fraudulent identification, and 600 cases involved people with two or more fraudulent identifications.
"We think we're getting those licenses off the streets, finding fraud that may not otherwise be found, addressing traffic-safety issues and hopefully reducing overall crime," said Beth Langen, administrator of policy and programs in the Driver Services Department of the Illinois Secretary of State's Office.
The program started in 1997, when the Illinois secretary of state took measures to detect and prevent identity theft statewide. When the agency decided to revamp the state's DMV services, the resulting RFP required a program to track identity fraud. The department first considered using fingerprint readers before it opted for facial recognition technology because pictures are a generally accepted part of visiting a DMV.
The Illinois Driver Services Department and the Secretary of State Police Department built the facial recognition program from the ground up with technology from Viisage, now part of L-1 Identity Solutions, which continues to maintain Illinois' program. The vendor helped build a database of facial recognition information from licenses that were either new or renewed with the department. It then implemented FaceExplorer, a face recognition application designed to handle large database mining and image management. The application looks for duplicate images from drivers' licenses and identification cards.
"It was an immediate success in that we immediately found instances on our database where people had, in fact, come in and gotten a driver's license and identification under different identities," Langen said.
When an Illinois DMV office captures an image, it's sent directly to the central image server, where the software creates a template for the picture it matches with thousands of other images in the database. The analysis is conducted within 25 servers by using algorithmic facial recognition, first matching images on previous licenses and identification cards, then matching the photos to other Illinois drivers' licenses with different names. Matches are sent to the Illinois Secretary of State Driver Services Fraud Unit, which conducts further analysis to determine whether there is a case for identity fraud.
The solution also enabled the secretary of state and law enforcement investigators to compare facial images from the driver's license image database with video surveillance photos, snapshots, sketches and composite photos.
The Illinois facial recognition program has helped detect thousands of fraud cases, including financial crimes, and on occasion, auto-theft rings, gang activity and welfare fraud. Oftentimes, fraudsters use multiple identities to commit crimes and escape detection.
In one instance, the program helped identify an Illinois resident who had seven false identities and purchased high-end automobiles to operate an auto-theft ring. The person was caught and received a 10-year prison sentence.
In 2005, the program's facial recognition matching dramatically improved when new cameras were installed and the L-1 Identity Solutions software was upgraded. The old version of the system identified three to 20 matches, whereas the upgraded system has a more refined matching capability and rarely displays a wrong match, Langen said. The new system is also speedier: It runs in real time, which is a big time-saver because the old system often took more than 12 hours to return matches.
The California DMV has been collecting drivers' digitized fingerprints since 1990 for consolidated data storage and to help track identity theft. However, the California DMV doesn't perform automatic checks to spot identity fraud. Instead, the agency conducts an investigation after a complaint has been filed. Yet fingerprint technology can be be less reliable than other forms of biometric technology in finding data fraud, The Orange County Register reported. California detectives found that identity thieves use liquid glue or hair spray to alter their fingerprints.
California's contract with the vendor that oversees the fingerprint program expires soon, California officials said. The state is actively seeking for a new contract that will upgrade the system to include facial recognition technology.
"Biometric technology has certainly improved quite a bit in the last few years," said Bernard Soriano, CIO and deputy director of the California DMV. "Right now, facial recognition has strengths, and other pieces of biometric technology have been advancing at a higher rate than others. In the past, biometric technology compared digital prints and iris scans, whereas if you look at facial scan, that technology is more sophisticated and has a lot more data points."
A Growth Industry With Error Rates
The biometrics industry will bring in an estimated $3.8 billion in 2008, with facial recognition biometrics accounting for $495 million, according to the International Biometric Group. The industry is expected to grow to $7.4 billion by 2012, according to the group.
Facial recognition applications have been available for more than a decade, but they have only recently gained widespread use in government. Facial recognition programs have copped up in Oregon, California, Colorado, Washington, Iowa, Kentucky, Wisconsin and West Virginia.
However, face recognition technology hasn't yet matured to become a viable solution for identifying people who are outdoors. While Viisage's FaceFinder has proved successful in a controlled environment, it generated so many errors when it was used with surveillance systems at the 2001 Super Bowl in Tampa, Fla., that it was considered a failure. Officials there found that facial recognition still falters when used in less-than-ideal conditions, such as when hats, sunglasses, movement and distance play a factor. The technology has also raised concerns over privacy and civil rights violations.
"In an uncontrolled environment, where you can't control lighting and you search at long distances, the technology just is not there yet," said Peter Cheesman, marketing director of the International Biometric Group. "It was definitely premature to have a test like [the Super Bowl]. It's getting there, but even at this point in a situation like the Super Bowl, it can work to find a person but not to scan the crowd for potentially harmful individuals."
In a controlled environment -- where lighting, head angle and distance of the subject can be directed -- facial recognition technology is considered reliable. A test by the National Institute of Standards and Technology found that facial recognition in a controlled environment has an error rate of 1 percent or less. L-1 Identity Solutions representatives say they are working to overcome the shortcomings of facial recognition technology.
Multiple Solutions, Multiple Uses
Biometric technology includes an assortment of identification techniques under research and development, including recognition of palm prints, fingerprints, hand geometry, dynamic signatures, vascular patterns, irises, voices and facial features.
Automated fingerprint identification systems (AFISs) are the largest and most mature biometric market space, with more than $1 billion in revenues in 2007, according to the International Biometric Group. AFIS processing and other identification systems are being used for law enforcement, background checks and some civil identification programs.
Biometric solutions are becoming widespread in places like casinos and airports, where face recognition can be combined with fingerprint or iris identification, Cheesman said. Iris recognition has proven to be the most effective biometric identification technology, but is far from becoming the hidden-eye scans in the science-fiction film Minority Report.
Since government organizations are increasing their investments in biometric-related technologies, the private sector is following the lead and has been busy developing products to meet the demand. Biometrics revenue growth is being driven mainly by government-mandated biometric implementation for employees, citizens and foreign nationals in national security-oriented applications, according to the International Biometric Group.
Biometric technology is expected to infiltrate more DMV programs across the country. In the coming years, biometric technology for identification purposes is expected to grow, especially with recent developments in service-oriented architecture for biometrics.
"The transition from government to enterprise and consumer in biometrics is faster and better," said Joseph Atick, chief strategic officer of L-1 Identity Solutions. "In the last five years, there has been an attitude change. People used to fear [biometric technology], but now they accept it if you can improve security and provide protection of assets. That attitude and shift is healthy for the industry, as long as the industry promotes the application that benefits the audience we deal with, which is human identity."