News

CBL putting a face on security

The UH Computational Biomedicine Lab is developing software that would have the potential to replace a personal identification number for transactions, which have been conducted more and more online in recent years.

Headed by UH professor Ioannis Kakadiaris, the CBL has developed new software called URxD which could have the potential to recognize the 3-D image of a person’s face.

"With the growing concern for security at the personal, national and international level, the University of Houston is pleased that Dr. Kakadiaris and his team have demonastrated a very promising technology for personal identification," UH Associate General Counsel for Research and Intellectual Property Management John Warren said in a release. "We look forward to its adoption by government and industry."

A problem with the current system of identification is that fingerprinting isn’t always accurate because some people don’t print well, and people touch many surfaces that others have touched which can lead to smudged prints Kakadiaris said. The two-dimensional images make a person look different because of the lighting.

"Accuracy is the name of the game in 3-D face recognition," Kakadiaris said in a release. "What makes our system so accurate is the strength of the variables that we use to describe a person’s face."

With the new software, the procedure of having one’s picture taken wouldn’t be long at all and could be conducted in the same amount of time a credit card is being swiped.

"It’s as instantaneous as taking a snapshot," Kakadiaris said.

The main factor to make a system work would be the widespread availability of specialized cameras that are small enough to fit on the small supermarket or drugstore counter.

Preventing identity theft isn’t the only plus to this new software, though. It could also help with the issue of national security, such as preventing mistaken identity incidents to occur by government agencies.

In order for this technology to be foolproof, a combination of biometrics, which could consist of systems such as iris scanning or finger printing along with the new software, would provide better security rather than just comparing three-dimensional images.

"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," Kakadiaris said. "The solution is to be able to tie your private information to your person in a way that cannot be compromised."

The availability of the software and camera in the near future is not known, nor is its user-friendliness toward potential consumers both in the public and private domains.

According to the Face Recognition Vendor Test, the new software URxD currently leads in this new technology, whose testing has been sponsored by several U.S. government agencies.

"This technology will have a positive impact on some of today’s hottest issues," Kakadiaris said.

"Imagine a day when you simply sit in front of your computer, and it recognizes who you are," he said. "Everything will be both easier and more secure, from online purchases to parental control of what Web sites your children can visit."

Leave a Comment