Stay up to date with notifications from The Independent

Notifications can be managed in browser preferences.

Massachusetts Institute of Technology scientists develop app that works out how memorable a face is

The technology was developed in a study of machine learning

Will Grice
Friday 18 December 2015 18:31 GMT
Comments
Jeremy Corbyn's face put through MIT's LaMem app
Jeremy Corbyn's face put through MIT's LaMem app (Getty / MIT)

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

An online tool has been developed by scientists that measures how memorable a face is.

The LaMem app scores faces on a scale of 0 - 1, with the most memorable scoring above 0.9 and least memorable scoring 0.8 and below.

The algorithm was developed by Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) and works by generating a heatmap that identifies which parts of an image are most memorable, with red signifying most memorable and blue least memorable.

The project was set up as a test of "machine learning", with CSAIL training LaMem by running several thousand images through the app, allowing it to gradually develop an understanding of what makes a memorable face.

Most of the faces that have been put through the app come out as very memorable due to the variance in each person's facial structure, although certain faces appear to be more recognisable than others.

An image of David Cameron's face came back with a reading of 0.894, while Jeremy Corbyn's scored 0.892. The LaMem website says singer Miley Cyrus's scored 0.958.

David Cameron's face put through MIT's LaMem app
David Cameron's face put through MIT's LaMem app (Getty / MIT)

The public version of the app can be tried out below - including testing your own face.

Speaking about the app, MIT researcher, Aude Oliva, told the Daily Mail, "While deep-learning has propelled much progress in object recognition and scene understanding, predicting human memory has often been viewed as a higher-level cognitive process that computer scientists will never be able to tackle.

"Well, we can, and we did.

CSAIL graduate student and lead author of the study Aditya Khosla said: "Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget.

"It's like having an instant focus group that tells you how likely it is that someone will remember a visual message."

The group now plan on tweaking the app to allow it to alter photos to make faces more memorable.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in