See what a child will look like using automated age-progression software (w/ video)

Apr 09, 2014 by Michelle Ma
Using one photo of a 3-year-old, the software automatically renders images of his face at multiple ages while keeping his identity (and the milk moustache). Credit: U of Washington

(Phys.org) —It's a guessing game parents like to ponder: What will my child look like when she grows up? A computer could now answer the question in less than a minute.

University of Washington researchers have developed software that automatically generates images of a young child's face as it ages through a lifetime. The technique is the first fully automated approach for aging babies to adults that works with variable lighting, expressions and poses.

"Aging photos of very from a single photo is considered the most difficult of all scenarios, so we wanted to focus specifically on this very challenging case," said Ira Kemelmacher-Shlizerman, a UW assistant professor of and engineering. "We took photos of children in completely unrestrained conditions and found that our method works remarkably well."

The research team has posted a paper on the new technique and will present its findings at the June IEEE Computer Vision and Pattern Recognition conference in Columbus, Ohio.

The shape and appearance of a baby's face – and variety of expressions – often change drastically by adulthood, making it hard to model and predict that change. This technique leverages the average of thousands of faces of the same age and gender, then calculates the visual changes between groups as they age to apply those changes to a new person's face.

This video is not supported by your browser at this time.
In each of these morphs, the left image is the starting input photo and the right image will transform to age 80 to show the automatic aging process.

More specifically, 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 correspondences between the averages from each bracket and calculates the average change in facial shape and appearance between ages. These changes are then applied to a new child's photo to predict how she or he will appear for any subsequent age up to 80.

The researchers tested their rendered images against those of 82 actual people photographed over a span of years. In an experiment asking random users to identify the correct aged photo for each example, they found that users picked the automatically rendered photos about as often as the real-life ones.

"Our extensive user studies demonstrated age progression results that are so convincing that people can't distinguish them from reality," said co-author Steven Seitz, a UW professor of computer science and engineering. "When shown images of an age-progressed child photo and a photo of the same person as an adult, people are unable to reliably identify which one is the real photo."

This is 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). Credit: U of Washington

Real-life photos of children are difficult to age-progress, partly due to variable lighting, shadows, funny expressions and even milk moustaches. To compensate for these effects, the algorithm first automatically corrects for tilted faces, turned heads and inconsistent lighting, then applies the computed shape and appearance changes to the new child's face.

Perhaps the most common application of age progression work is for rendering older versions of missing children. These renderings usually are created manually by an artist who uses photos of the child as well as family members, and editing software to account for common changes to a child's face as it ages, including vertical stretching, wrinkles and a longer nose.

But this process takes time, and it's significantly harder to produce an accurate image for children younger than age 5, when facial features more closely resemble that of a baby.

The automatic age-progression software can run on a standard computer and takes about 30 seconds to generate results for one face. While this method considered gender and age, the research team that also includes UW doctoral student Supasorn Suwajanakorn hopes to incorporate other identifiers such as ethnicity, and cosmetic factors such as hair whitening and wrinkles to build a robust enough method for representing every human face.

"I'm really interested in trying to find some representation of everyone in the world by leveraging the massive amounts of captured face photos," Kemelmacher-Shlizerman said. "The aging process is one of many dimensions to consider."

Explore further: Face it: Instagram pictures with faces are more popular

add to favorites email to friend print save as pdf

Related Stories

Face it: Instagram pictures with faces are more popular

Mar 20, 2014

Like them or not, there's more proof that selfies aren't going away any time soon. Georgia Institute of Technology and Yahoo Labs researchers looked at 1.1 million photos on Instagram and found that pictures ...

New technology to predict future appearance

Mar 11, 2011

A Concordia graduate student has designed a promising computer program that could serve as a new tool in missing-child investigations and matters of national security. Khoa Luu has developed a more effective computer-based ...

Recommended for you

Avatars make the Internet sign to deaf people

Aug 29, 2014

It is challenging for deaf people to learn a sound-based language, since they are physically not able to hear those sounds. Hence, most of them struggle with written language as well as with text reading ...

Chameleon: Cloud computing for computer science

Aug 26, 2014

Cloud computing has changed the way we work, the way we communicate online, even the way we relax at night with a movie. But even as "the cloud" starts to cross over into popular parlance, the full potential ...

User comments : 5

Adjust slider to filter visible comments by rank

Display comments: newest first

Tangent2
2 / 5 (5) Apr 09, 2014
In the example picture strip, the child on the left (generated by the algorithm) looks like he has down syndrome in each iteration. Is that a feature of the software, to make the children look handicap?
Pejico
Apr 09, 2014
This comment has been removed by a moderator.
24volts
4.7 / 5 (3) Apr 09, 2014
I wish they would put a link to that software to download it or put in on a website you could try pictures with.
Tangent2
not rated yet Apr 10, 2014
Is the child at the left really generated by the algorithm? As far I understand the article, it does represent the starting data instead. Maybe the down syndrome isn't at the side of software..


If it's not the software, then it has to be the child, but it is not the child, as you can observe the right image in each sequence does not have the down syndrome effect and that is the real picture of the child right now. That being the case, it most certainly is the software doing this.
jfleckenstein
not rated yet Apr 16, 2014
Seems very peculiar that the aging algorithm would EXACTLY match the change in hair styles at the various ages. It is suspect enough that the hair color matches so closely when the childs' hair at age 3 was so blonde. But there is no way that the hair length, cut and hair direction (see age 10) could match the way it is depicted unless there was post manipulation of the images.
jwilcos
not rated yet May 29, 2014
Pretty cool, nice job by the team. This would be a very popular app. Bet everyone wants to see what their kids would look like grown up, and what they themselves would look like 20 or 30 years down the road. The other obvious use is for missing kids. At $4.99, the app would sell like hotcakes.