University of Texas Arlington

ARLINGTON - The National Science Foundation has awarded a UT Arlington computer science engineering professor a five-year, $513,000 Early Career Development grant to further develop a computer recognition system that will become a visual dictionary for American Sign Language.

Vassilis Athitsos demonstrates the sign language recognition system he is developing with National Science Foundation funding

Vassilis Athitsos, an assistant professor in computer science and engineering at The University of Texas at Arlington, has received the grant, which will fund continuing work on computer vision technology.

The new project, “Large Vocabulary Gesture Recognition for Everyone: Gesture Modeling and Recognition Tools for System Builders and Users,” will automatically annotate, recognize and index large vocabularies of gestures.

To find the meaning of a particular sign, the user would form the sign in view of a camera atop a computer. The recognition system would compare the gesture with thousands of images stored in the computer’s database, display a selection of similar images and allow the user to select the most appropriate meaning.

"I'm happy if we can get it down to 10 selections," Athitsos said. “It’s kind of like a Google search for gestures that are used in sign language.”

Athitsos hopes to eventually team with producers of American Sign Language dictionaries to make a sign recognition system widely available and downloadable from the Internet. Future generations of the online sign language dictionary could reflect regional "dialects," he said, because signs can vary from region to region.

"Our technology will also be applied to other sign languages around the world, as certainly there is a large number of different sign languages used in different countries,” Athitsos said.

Bill Carroll, dean of the UT Arlington College of Engineering, said Athitsos’ research has an immediate and positive impact on the lives of people.

“It’s the kind of practical, real-world research that we land here at UT Arlington,” Carroll said.

Athitsos initially became interested in decoding American Sign Language while taking a college course in the subject.

“I was a horrible student; I had to page through a book and look at the signs until I recognized something,” he said. “My professor at the time told me no one had tried to make a computer-based, sign lookup system.”

As an additional outreach activity, Athitsos will help organize computer science summer camps for junior high and high school students intended to attract young people to careers in science.

Athitsos’ work is representative of the research taking place at The University of Texas at Arlington, a comprehensive research institution of nearly 33,000 students in the heart of North Texas. Visit www.uta.edu to learn more.

###

The University of Texas at Arlington is an Equal Opportunity and Affirmative Action employer.