How UW's Age-Progression Software Could Help Find Missing Kids

KUOW | By Andy Hurst,

Published April 21, 2014 at 1:48 PM AKDT

1 of 2

A single photo of a child (far left) is age progressed (left in each pair) and compared to actual photos of the same person at the corresponding age (right in each pair).

Courtesy of the University of Washington

2 of 2

Using one photo of a 3-year-old boy, the software automatically renders images of his face at multiple ages while keeping his identity (and the milk mustache.)

Courtesy of the University of Washington

Ross Reynolds talks with Robert Lowery, vice president of the Missing Children Division at the National Center for Missing and Exploited Children, about the new automated age-progression software developed at the University of Washington.

The software can be used to predict what someone will look like as an adult from a single childhood photograph, and the results are astonishingly accurate.

In the video below, the left image is the input photo and the right image will age to 80 years to show the automated aging process.