iStock
iStock

Ruined a Photo By Blinking? Facebook Can Fix It With AI

iStock
iStock

Next time you blink in an otherwise flawless photo, don't be so quick to hit the "delete" button on your phone. As The Verge reports, Facebook is testing a new feature that uses artificial intelligence to make closed eyes look naturally open.

Facebook engineers Brian Dolhansky and Cristian Canton Ferrer described the technology behind the AI in a paper published June 18. They used a type of machine learning called generative adversarial network or GAN. It works by looking at a database of pictures and using that information to generate new imagery where there wasn't any before.

This type of AI has been used to design clothing and video game levels in the past. To get it to work with faces, Facebook engineers showed the system photos taken of people when their eyes were open. After "learning" the subject's eye shape, size, and color, the AI used that data to superimpose a new set of eyes over the blinking lids. The feature still has some trouble working with glasses, long bangs, and pictures taken at an angle, but when it does what it's supposed to, it's hard to tell the photo was ever retouched.

Faces with blinking and open eyes.
Facebook

Facebook isn't the first company to use AI to salvage photographs with closed eyes. In 2017, Adobe added an "Open Closed Eyes" feature to Photoshop Elements that also uses AI to generate a pair of eyes that match those of the blinking subject. For it to work, users first have to show the system several photos of the subject with their eyes open.

Facebook, which already holds a database of pictures of many of its users, seems like a perfect fit for this type of technology. The social media site is still testing it out, but based on the success of early experiments, they may consider making it available to users in the not-too-distant future. And because Facebook owns Instagram, it's possible that the eye-opening feature will eventually be applied to Instagram posts and Stories as well.

[h/t The Verge]

Marshall McLuhan, the Man Who Predicted the Internet in 1962

Futurists of the 20th century were prone to some highly optimistic predictions. Theorists thought we might be extending our life spans to 150, working fewer hours, and operating private aircrafts from our homes. No one seemed to imagine we’d be communicating with smiley faces and poop emojis in place of words.

Marshall McLuhan didn’t call that either, but he did come closer than most to imagining our current technology-led environment. In 1962, the author and media theorist, predicted we’d have an internet.

That was the year McLuhan, a professor of English born in Edmonton, Canada on this day in 1911, wrote a book called The Gutenberg Galaxy. In it, he observed that human history could be partitioned into four distinct chapters: The acoustic age, the literary age, the print age, and the then-emerging electronic age. McLuhan believed this new frontier would be home to what he dubbed a “global village”—a space where technology spread information to anyone and everyone.

Computers, McLuhan said, “could enhance retrieval, obsolesce mass library organization,” and offer “speedily tailored data.”

McLuhan elaborated on the idea in his 1962 book, Understanding Media, writing:

"Since the inception of the telegraph and radio, the globe has contracted, spatially, into a single large village. Tribalism is our only resource since the electro-magnetic discovery. Moving from print to electronic media we have given up an eye for an ear."

But McLuhan didn’t concern himself solely with the advantages of a network. He cautioned that a surrender to “private manipulation” would limit the scope of our information based on what advertisers and others choose for users to see.

Marshall McLuhan died on December 31, 1980, several years before he was able to witness first-hand how his predictions were coming to fruition.

nextArticle.image_alt|e
Arthur Shi, iFixit // CC BY-NC-SA 3.0
The New MacBook Has a Crumb-Resistant Keyboard
Arthur Shi, iFixit // CC BY-NC-SA 3.0
Arthur Shi, iFixit // CC BY-NC-SA 3.0

Soon, you won’t have to worry about ruining your Macbook’s keyboard with muffin crumbs. The 2018 MacBook Pro will feature keys specifically designed to withstand the dust and debris that are bound to get underneath them, according to Digital Trends. The keyboard will also be quieter than previous versions, the company promises.

The latter feature is actually the reasoning Apple gives for the new design, which features a thin piece of silicon stretching across where the keycaps attach to the laptop, but internal documents initially obtained by MacRumors show that the membrane is designed to keep debris from getting into the butterfly switch design that secures the keycaps.

Introduced in 2015, Apple’s butterfly keys—a change from the traditional scissor-style mechanism that the company’s previous keyboards used—allow the MacBook keyboards to be much thinner, but are notoriously delicate. They can easily become inoperable if they’re exposed to dirt and debris, as any laptop is bound to be, and are known for becoming permanently jammed. In fact, the company has been hit with multiple lawsuits alleging that it has known about the persistent problem for years but continued using the design. As a result, Apple now offers free keyboard replacements and repairs for those laptop models.

This new keyboard design (you can see how it works in iFixit's very thorough teardown), however, doesn’t appear to be the liquid-proof keyboard Apple patented in early 2018. So while your new laptop might be safe to eat around, you still have to worry about the inevitable coffee spills.

[h/t Digital Trends]

SECTIONS

arrow
LIVE SMARTER
More from mental floss studios