Communications of the ACM
When a Computer Ages You
The faces of two Washington Post staffers (each shown as their actual ages at left) are "aged" using computer technology developed by researchers in the Face Aging Group at the University of North Carolina, Wilmington.
Credit: The Washington Post
Biodemographer Jay Olshansky and computer scientist Karl Ricanek are hoping to harness facial-recognition and age-progression technology to estimate people's life spans and future health based only on a photograph.
Olshansky says the idea came to him during a conversation with an insurance underwriter, who noted people who live longer tend to look younger than other people their age. Together with Ricanek, who has developed facial-recognition technology for government and law enforcement, and a team of biostatisticians and computer scientists, he is developing the online database Face My Age. Users will be invited to submit a photograph of themselves, which then will be analyzed using facial-recognition algorithms that also account for demographic information like age, sex, race, education level, and smoking history to estimate their apparent age.
Olshansky hopes the program will eventually be able to tell users the apparent age of different parts of their face and ultimately predict how long they will live and how healthy they will be in old age.
The researchers expect the Face My Age website to produce increasingly more accurate assessments and predictions as more people participate. "Imagine taking your iPhone and snapping a selfie and putting it into our website and discovering that your eyes are that of a 50-year-old, your lips are that of a 70-year-old, your cheeks are that of a 50-year-old," Ricanek says.
From The Washington Post
View Full Article - May Require Free Registration
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found