How to Make My Baby Look Like 100 Years Old
Apr 9, 2014
Automatic age-progression software lets you meet how a child will age
It's a guessing game parents similar to ponder: What will my child look similar when she grows up? A calculator could now reply the question in less than a infinitesimal.
University of Washington researchers have developed software that automatically generates images of a immature kid's confront as it ages through a lifetime. The technique is the first fully automated approach for crumbling babies to adults that works with variable lighting, expressions and poses.
"Aging photos of very immature children from a unmarried photo is considered the most difficult of all scenarios, so we wanted to focus specifically on this very challenging instance," said Ira Kemelmacher-Shlizerman, a UW assistant professor of reckoner science and engineering science. "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 nowadays its findings at the June IEEE Calculator Vision and Pattern Recognition conference in Columbus, Ohio.
The shape and advent of a baby'southward face – and variety of expressions – ofttimes modify drastically by adulthood, making it hard to model and predict that change. This technique leverages the boilerplate of thousands of faces of the same age and gender, and then calculates the visual changes between groups as they age to apply those changes to a new person'due south face.
More specifically, the software determines the boilerplate pixel arrangement from thousands of random Cyberspace photos of faces in dissimilar 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 eighty.
The researchers tested their rendered images against those of 82 actual people photographed over a span of years. In an experiment request random users to identify the correct aged photo for each example, they plant that users picked the automatically rendered photos nearly as oftentimes equally 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 reckoner science and engineering. "When shown images of an age-progressed child photograph and a photograph of the same person as an adult, people are unable to reliably identify which ane is the real photograph."
Real-life photos of children are hard to age-progress, partly due to variable lighting, shadows, funny expressions and even milk moustaches. To recoup for these effects, the algorithm commencement automatically corrects for tilted faces, turned heads and inconsistent lighting, and then applies the computed shape and advent changes to the new child'due south face.
Mayhap the near common awarding of age progression work is for rendering older versions of missing children. These renderings normally are created manually past an creative person who uses photos of the child also every bit family unit members, and editing software to account for common changes to a kid's face as it ages, including vertical stretching, wrinkles and a longer nose.
Just this process takes fourth dimension, and it's significantly harder to produce an accurate paradigm for children younger than age 5, when facial features more closely resemble that of a baby.
The automated age-progression software tin can run on a standard computer and takes well-nigh 30 seconds to generate results for one face. While this method considered gender and age, the research team that too includes UW doctoral pupil Supasorn Suwajanakorn hopes to contain other identifiers such as ethnicity, and cosmetic factors such as hair whitening and wrinkles to build a robust enough method for representing every human being face.
"I'chiliad 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 i of many dimensions to consider."
This research was funded by Google and Intel Corp.
###
For more information, contact Kemelmacher-Shlizerman at kemelmi@cs.washington.edu or 206-616-0621.
Tag(s): Higher of Applied science • Ira Kemelmacher-Shlizerman • Paul Grand. Allen Schoolhouse of Computer Science & Engineering • Steve Seitz
Source: https://www.washington.edu/news/2014/04/09/see-what-a-child-will-look-like-using-automated-age-progression-software/
0 Response to "How to Make My Baby Look Like 100 Years Old"
Post a Comment