New software makes your pictures more memorable without changing your face

Algorithims created by examining 'facial memorability' database could be used to improve your chances in a job application

Click to follow
The Independent Tech

Would you like to stand out more from the crowd? Scientists from the Massachusetts Institute of Technology (MIT) might have the answer, with the discovery of a new algorithm that makes faces more memorable.

By subtle exaggeration of already distinctive facial features (arched eyebrows or sharp cheekbones for example) the researchers were able to increase the memorability of a face without drastically changing the individual’s appearance.

"We want to modify the extent to which people will actually remember a face," said Aditya Khosla, one of the paper’s lead authors.

"This is a very subtle quality, because we don't want to take your face and replace it with the most memorable one in our database, we want your face to still look like you.”

The researchers suggest that the final algorithm could work from a smartphone, modifying users’ digital pictures to create more memorable versions for social networking sites and job applications.

Another potential application would be the film industry, where extras in the background could have their faces altered to make them less memorable, further drawing attention to the movie’s stars.

To make the software the researchers created a database of more than 2,000 faces and awarded each with a ‘memorability score’ based on how easily volunteers’ recognized the individuals.

“It’s really like applying an elastic mesh onto the photograph that slightly modifies the face,” said researcher Aude Oliva. “The face still looks like you, but maybe with a bit of lifting.”

Olivia also noted that making a face more memorable can be more important than simply standing out from a crowd of faces – it can also make a person seem more likeable.

"If we tag a person with familiarity, because we think this is a face we have seen before, we have a tendency to like it more, and for instance to think the person is more trustworthy,” she said.

Click here to read the paper in the full.