Science

New software accurately predicts what your children will look like as adults

View 6 Images
New software from the University of Washington can accurately predict what your kid will look like as an adult (Image: University of Washington)
The algorithm only requires a single baby picture as the input (Image: University of Washington)
New software from the University of Washington can accurately predict what your kid will look like as an adult (Image: University of Washington)
New software from the University of Washington can accurately predict what your kid will look like as an adult (Image: University of Washington)
The algorithm applied to mens faces (Image: University of Washington)
The procedure for aging a baby face (Image: University of Washington)
From a single input (top), the software can create the composites of what the person will look like at various ages (left) which closely match actual pictures (right) (Image: University of Washington)
View gallery - 6 images

If you're a parent wondering what your child will look like as an adult, now you don't need to wonder anymore. Researchers at the University of Washington claim to have developed software that can accurately predict what a child will look like as an adult, up to the age of 80. The technique can even work from poorly lit photos, and could prove a big help in missing persons cases.

Predicting what a child will look like as an adult from a single baby picture is extremely difficult, even for the people whose profession it is to create facial composites for the police. Try to get a completely automated software to do the same, and you'll run into an additional layer of problems in the source picture, including poor lighting, strange facial expressions, and other imponderables like, say, a milk mustache.

But researchers led by assistant professor Ira Kemelmacher-Shlizerman say that they've managed to create a computer algorithm that can actually do a much better job than its human counterpart.

New software from the University of Washington can accurately predict what your kid will look like as an adult (Image: University of Washington)

The software relies on a database of thousands of faces, grouped by gender and age. For each age bracket, it determines the average pixel distribution of various facial features, and then calculates how those features change from one bracket to the next, as age advances.

The system's algorithm then takes a baby picture as input. After correcting for tilted faces, turned heads and inconsistent lighting, the software applies the age bracket-related changes to the child’s photo to predict how he or she will look like as an adult, reportedly guessing his or her appearance with remarkable accuracy, up to the age of 80.

In order to test the algorithm's performance, Prof. Kemelmacher-Shlizerman and colleagues collected the actual pictures of 82 people over a span of several years, and fed the subject's baby pictures to the software. From that single input, the program-generated facial composites were so close a match to actual photos that when a group of people was presented with the original and the rendered pictures side by side, they were unable to tell which was which.

From a single input (top), the software can create the composites of what the person will look like at various ages (left) which closely match actual pictures (right) (Image: University of Washington)

The system could prove extremely useful in missing person cases. Police facial composites are usually created manually, taking photos of the child and family members and manipulating a best guess of how the face may have aged over the years. This algorithm, on the other hand, has proven remarkably accurate and, run on a normal computer, it provides an answer in about 30 seconds.

A freely available paper (PDF) published by the researchers explains in detail how the algorithm works. Prof. Kemelmacher-Shlizerman told us that the technology will soon be made available to the public.

The video below shows the software in action. On the left is the original photo, while on the right the algorithm outputs the prediction of what the child will look like as an adult.

Source: University of Washington

View gallery - 6 images
  • Facebook
  • Twitter
  • Flipboard
  • LinkedIn
9 comments
Milton
mind blown!
Bob
How does it compensate for grey hair or baldness?
Chris Reyes
So, with all this research, I see the same pitfall and that is a failure to adequately include people of color. Having read the research, they seem to have had 40K different faces. It would have been good to see how effective they were with darker skin tones. Not one example in their paper shows a person of color. With something so beneficial to missing person cases, it would be unfortunate to see it applied so disparately and unconsciously perpetuating the myth of relative worth often reported in these cases.
Beaugrand_RTMC
When can I download this app?
jingleburp
This computer software which supposedly predicts how kids will look as adults is likely every bit as accurate as the Global warming algorithms used to predict future climate. All of those programs were proven to be completely bunk as this one will be too. Think of all the people you knew as kids and how they look nothing like they did as kids now that they are adults. Too many variables (genetic, environmental and others) to account for here.
Buzzclick
And what if they put on weight? Is there enough wrinkles in the composites? Bald/hairy? Beard/shaven? Dyed/gray?...
This software still has a ways to go, but it's a start.
DKB132
I may be missing something but, I don't believe the claim being made. Looking at the five examples of side by side images, all of the hair is exactly the same. So am I to believe the program is able to accurately predict hair styles too in the childs future too? Hair is identical in all photos.
JulieEasterling-Collins
How do I down load this Iam trying to search for my daughter I only have a picture of her when she was 4 I need to see what she would Look like today
AhmadFaisal
can the process be reversed, i'm curious how my grand mother's face when 19 years old, even much younger.