Trying to picture yourself with a completely different look — long hair, curly hair, no hair — or imagining yourself in a different culture or time period has been made easier thanks to a new University of Washington personalized image search engine called Dreambit.
Developed by Ira Kemelmacher-Shlizerman, UW assistant professor of computer science and engineering, Dreambit lets us try on a new look without actually making the physical leap.
According to a report in UW Today, users can upload an image, type in a search term such as “dark hair” or “1970s” and the software’s algorithms mine the internet for images in that category that allow the person’s face to be seamlessly mapped onto the results.
If you’ve ever seen images of missing children or escaped convicts altered to show a change in appearance through age or disguise, Dreambit does draw on previous research conducted at the UW and elsewhere that uses similar techniques.
Kemelmacher-Shlizerman and her team previously developed automated age progression software that focused only on a person’s face. Dreambit adds varied hairstyle options and other contextual elements.
The whole process goes a bit beyond the comedy element we can get from a variety of smartphone apps, such as Old Booth or Aging Booth, which take a run at putting your face through an aging process or cultural reimagining.
And while no one would ever advocate for actor George Clooney to return to his mullet days, Kemelmacher-Shlizerman couldn’t resist running the hunky star through the process to see what he would look like with curly hair. Actress Keri Russell got the treatment, too.
“This is a way to try on different looks or personas without actually changing your physical appearance,” Kemelmacher-Shlizerman told UW Today. “While imagining what you’d look like with a new hairstyle is mind blowing, it also lets you experiment with creative imaginative scenarios.”
