Computers taught to create attractive people just for you

Some of the 'attractive' faces the computers generated.
Some of the 'attractive' faces the computers generated. Photo credit: University of Helsinki

Time to close that incognito tab - computers can now generate attractive people just for you, simply by reading your brain waves. 

Previous attempts by artificial intelligence to produce hot people worked, but the results weren't specific to anyone's particular kinks.

"In our previous studies, we designed models that could identify and control simple portrait features, such as hair colour and emotion. However, people largely agree on who is blond and who smiles," said Michiel Spapé of the University of Helsinki. 

"Attractiveness is a more challenging subject of study, as it is associated with cultural and psychological factors that likely play unconscious roles in our individual preferences. Indeed, we often find it very hard to explain what it is exactly that makes something, or someone, beautiful - beauty is in the eye of the beholder."

Dr Spapé's team used artificial intelligence to create hundreds of portraits and showed them to 30 volunteers whilst tracking their brain patterns via electroencephalography (EEG). 

"It worked a bit like the dating app Tinder: the participants 'swiped right' when coming across an attractive face. Here, however, they did not have to do anything but look at the images. We measured their immediate brain response to the images."

The computer then took that information and used it to create more faces, combining features that seemed to get the participants' hearts racing - or in this case, brainwaves pulsing. 

The new images beat the old ones 87 percent of the time.

"The study demonstrates that we are capable of generating images that match personal preference by connecting an artificial neural network to brain responses," said Dr Spapé.

"Succeeding in assessing attractiveness is especially significant, as this is such a poignant, psychological property of the stimuli. Computer vision has thus far been very successful at categorising images based on objective patterns. By bringing in brain responses to the mix, we show it is possible to detect and generate images based on psychological properties, like personal taste."

There's more to the work than just making pretty fake people, though. Dr Spapé says if it's "possible in something that is as personal and subjective as attractiveness, we may also be able to look into other cognitive functions such as perception and decision-making. 

"Potentially, we might gear the device towards identifying stereotypes or implicit bias and better understand individual differences."

The study was published in journal IEEE Transactions on Affective Computing