Face recognition as a unique biometric is growing slowly in certain corporate and consumer applications, but researchers at the University of Houston (UH) are trying to make the technology far more ubiquitous and secure: they want it to replace the dozens of personal identification numbers (PIN), passwords and credit card numbers everyone uses every day.
University researchers developed the URxD face recognition software that uses a three-dimensional snapshot of a person's face to create a unique biometric identifier.
The UH designed and built a prototype field-deployable 3D face recognition system that consists of a 3dMDTM optical scanner using a 1-pod configuration, which is connected to a PC. A webcam captures a continuous video stream which is used to detect whether a person is facing the 3D camera. When the subject is facing the camera and remains relatively still for more than two seconds, the system triggers the optical scanner and the 3D data of the individual's face are captured. The system can either enroll the subject into the database, or perform a scenario-specific task. In an identification scenario, the system will display the closest 5 datasets to the operator. In a verification scenario, the system will determine whether the subject is who they claim to be, based on a preset distance threshold, UH says.
The system determines not only the characteristics of each face, but also whether the person is wearing glasses, allowing for a practical system which offers high accuracy. So far, face recognition methods have focused on appearance - capturing, representing, and matching facial characteristics as they appear on two-dimensional images in the visible spectrum. This is quite challenging to machine recognition because such characteristics vary with orientation, age, habits (beard etc)), and illumination. Instead, the UH system uses three-dimensional information.
The system was highly rated by The National Institute of Standards and Technology (NIST) in its annual Face Recognition Vendor Test (FRVT) 2006 and the Iris Challenge Evaluation (ICE) 2006. NIST said the FRVT looks at face recognition from high-resolution still images and three-dimensional (3D) face images, and measures performance for still images taken under controlled and uncontrolled illumination. Face and iris are two biometrics that have been developed over the last 20 years. Face recognition is a vibrant area of biometrics with active research and commercial efforts. The FRVT 2006 is the latest in a series of evaluations for face recognition that began in 1993. With the expiration of the Flom and Safir iris recognition patent in 2005, iris recognition algorithm development has become more active. The ICE 2006 is the first independent evaluation for iris recognition algorithms, NIST said.
"Remembering dozens of personal identification numbers and passwords is not the solution to identity theft. PINs and passwords are not only inconvenient to memorize, but also are impractical to safeguard. In essence, they merely tie two pieces of information together; once the secret is compromised, the rest follows. The solution is to be able to tie your private information to your person in a way that cannot be compromised," said Eckhard Pfeiffer Professor of Computer Science and director of the UH Computational Biomedicine Laboratory.
Biometric systems, usually fingerprint and iris readers and the like are the most widely used biometric security systems used. For example, the British government - beset by fears of terrorists, crime and illegal immigration - has drawn up wide plans to drop a tight electronic curtain over its borders over the next seven years. It is testing several technologies as part of its "e-Borders" program, which aims for more thorough oversight over travelers coming to the U.K.
So far, more than 60,000 U.K. citizens have participated in a program that uses biometric data to process people faster through immigration lines. The Iris Recognition Immigration System, or IRIS, stores a person's iris pattern and passport details in a database, which enables them to pass through immigration electronically without a face-to-face encounter. The U.K. government says it has facilitated 210,000 border crossings since its debut in March 2006.
NIST last year released the Multimodal Biometric Application Resource Kit (MBARK), an open source middleware package that enables you to plug in biometric sensors from different manufacturers. The kit also contains templates and sample apps. All the details and the software can be downloaded from the NIST Web site.