University of Texas at Dallas (UTD) researchers are working with the U.S. Department of Defense to find the most accurate and cost-effective way to recognize individuals who might post a security risk. UTD professor Alice O'Toole and her team are examining facial-recognition software to determine where the algorithms succeed and where they fail.
The researchers are comparing the algorithms to human test subjects in how well they can correctly identify matching pairs of human faces. So far, the best algorithms have performed better than humans at identifying faces, according to O'Toole. "Because most security applications rely primarily on human comparisons up until now, the results are encouraging about the prospect of using face recognition software in important environments," she says.
However, combining the software with human evaluation methods produces the best results. By using the software to spot potential high-risk individuals and then combining that information with the judgment of a person, nearly 100 percent of matching faces were identified, O'Toole says.
From University of Texas at Dallas
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA
No entries found