Images of our faces exist in many important databases. Can these images continue to identify us as we age?
Michigan State University biometrics expert Anil Jain and team set out to investigate how facial aging affects the performance of automatic facial recognition systems. They also looked at the implications of identifying criminals and determining when ID's need to be renewed.
“We wanted to determine if state-of-the-art facial recognition systems could recognize the same face imaged multiple years apart, such as at age 20 and again at age 30,” said Jain, University Distinguished Professor of computer science and engineering. “This is the first study of automatic facial recognition using a statistical model and large longitudinal face database.”
Jain and doctoral student Lacey Best-Rowden found that 99 percent of the face images are recognized up to six years later. Yet results show that the accuracy of facial recognition declines when pictures are taken more than six years apart. The decrease in face recognition accuracy is person-dependent. This is because some people age faster than others. Differences in aging are due to lifestyle, health conditions, environment or genetics.
"This research shows the importance of capturing new images every four to five years to reduce the number of false positives or chance of not finding a candidate in a facial recognition search due to length of time between captures,” said Pete Langenfeld, manager in the Biometrics and Identification Division at the Michigan State Police.
Jain’s team studied two police mugshot databases of repeat criminal offenders. Each offender had at least four images acquired over at least a five-year period. The total number of repeat offenders studied was 23,600. Mugshot databases are the largest source of facial aging photos available. They have well-controlled standards to ensure the photos are uniform. These are the largest facial-aging databases studied to date due.
Academic research has enabled automated face recognition to play an large role in the criminal justice system. But there has been a lack of research about the proper usage of these systems, said Brendan Klare, CEO of Rank One Computing, a major supplier of face recognition software.
“This comprehensive study by Jain and Best-Rowden provides for the first time an unprecedented body of knowledge regarding the limits of automated face recognition."
The paper will appear in the IEEE Transactions on Pattern Analysis & Machine Intelligence journal. The study was conducted in collaboration with the National Institute of Standards and Technology.
Source: Michigan State University