Features Story Archive

Alumni Spotlight: Technology at Face Value

Dr. Shalini Gupta

Dr. Shalini Gupta earned a master's and doctor's degree in Electrical and Computer Engineering from the Cockrell School in 2004 and 2008.

The human face does more than help us tell each other apart. Studies have suggested that our perceptions of attractiveness and personality traits — even intangible qualities such as trustworthiness and sincerity — could be based on instinctive responses to certain facial features.

But breakthroughs in facial recognition technology have been used in recent years to screen for criminals, to catch cheaters at casinos and even to recommend products at vending machines.

And now, thanks to an alumna and her faculty advisers at the Cockrell School of Engineering, digital human face recognition could also be used to help perform reconstructive surgery for everyone from cancer patients to children born with disfigurements.

Dr. Shalini Gupta of Nvidia Corp., who earned a master's and doctor's degree in Electrical and Computer Engineering from the Cockrell School in 2004 and 2008, worked with a team to develop novel algorithms for 3-D human face recognition in a project supervised by the university's Laboratory for Image and Video Engineering and the Biomedical Informatics Lab, located in the Department of Electrical and Computer Engineering and the Department of Biomedical Engineering, respectively.

The team, led by BME Professor Mia Markey and ECE Professor Alan Bovik, mapped and measured the facial features of 118 subjects, recording proportions — such as the distance between eye corners and the width of the nose — that make each 3-D model unique. The algorithms they created outperformed several of the standard face recognition methods that are currently in use, and Markey, Bovik and others are now working with MD Anderson Cancer Center and Dell's Children Hospital to move the research from the lab to the doctor's office.

An important contribution of Gupta's research in college was to create a technique to automatically locate 10 specific facial reference points, or fiduciary points, on 3-D facial models

The facial point detection algorithms were developed in the context of 3-D face recognition algorithms that can be used for facial plastic surgery as well to automatically detect facial fiducial points on 3-D facial models.

Such work will enable doctors, who traditionally would have to measure a person's face manually to determine the best route for reconstructive surgery, to instead take a series of photos of the patient's face that can be turned into 3-D facial models that show more accurate measurements.

Commercial Products

As facial recognition generates buzz in scientific circles, the technology is also making an impact in the business world, Gupta said. She outlined the future of the field recently at The Austin Forum on Science, Technology and Society.

"All of the big tech companies are investing R&D dollars in this area," she said. "Google, Microsoft — everyone is looking at it. It's a very hot topic."

Google made a foray into facial recognition when it acquired Neven Vision — a company that pioneered early visual search and analysis technologies — in 2006. Its Picasa program includes a feature that scans online photo albums and automatically identifies people who appear in multiple images and sorts the photos accordingly.

Apple's iPhoto and Microsoft's Windows Live Photo Gallery have similar tools, and in December, Facebook announced a new feature called Tag Suggestions that will identify friends' faces in uploaded photos so they can be tagged more efficiently.

These 2-D systems became available to consumers in the last decade or so, but Gupta said many companies have already begun to shift toward developing 3-D and mobile face recognition technologies.

Once perfected, 3-D systems could be even more useful in identifying people in real-world environments because they account for variations in facial structure and pose. Still, there are a number of hurdles that must be overcome before biometrics technology achieves its full potential.

"I don't think the facial recognition problem is solved. Specifically, it is not solved for unconstrained environments where we can't control backgrounds, lighting conditions and poses," Gupta said. "These are all things at need to be resolved before we can get to a point of high accuracy."

Medical institutions, including the Dell Children's Hospital, have already begun to use these 3-D facial imaging systems to take measurements and screen patients before surgery.

Gupta says there are numerous opportunities for the technology that might have seemed impossible just a few years ago.

"When I started working in this area, I didn't realize how real it was," she said. "It's out there. People are working on it and developing products. It seems like science fiction, but it's real."


An extended version of this story originally appeared on the Texas Enterprise Web site.