University of Washington (UW) researchers have developed software that automatically generates images of a child's face as it ages through a lifetime. The researchers say their software is the first fully automated approach for aging babies to adults that works with variable lighting, expressions, and poses.
"We took photos of children in completely unrestrained conditions and found that our method works remarkably well," says UW professor Ira Kemelmacher-Shlizerman.
The technique leverages the average of thousands of faces of the same age and gender before calculating the visual changes between groups as they age to apply those changes to a new person's face. The software determines the average pixel arrangement from thousands of random Internet photos of faces in different age and gender brackets. An algorithm then finds similarities between the averages from each bracket and calculates the average change in facial shape and appearance between ages.
"Our extensive user studies demonstrated age progression results that are so convincing that people can't distinguish them from reality," says UW professor Steven Seitz. He notes the automatic age-progression software runs on a standard computer and takes about 30 seconds to generate results for one face.
From UW News
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found