Researchers from the Massachusetts Institute of Technology have created a computer algorithm that can predict the memorability of an image almost as accurately as a human. The findings, are planned for use in an app that will subtly alter photos in order to make them more memorable.
"Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget," Aditya Khosla, lead author of the paper, said in a press release. "It's like having an instant focus group that tells you how likely it is that someone will remember a visual message."
In addition to the app that will increase photo memorability, the researchers hope that the algorithm will also help in the improvement of ad content, social media posts and teaching resources.
"This sort of research gives us a better understanding of the visual information that people pay attention to," said Alexei Efros, an associate professor of computer science at the University of California at Berkeley, according to Phys.org. "For marketers, movie-makers and other content creators, being able to model your mental state as you look at something is an exciting new direction to explore."
The study also sheds light on the nature of human memory and poses potential to be used for its improvement.
"You might expect that people will acclimate and forget as many things as they did before, but our research suggests otherwise," Efros said. "This means that we could potentially improve people's memory if we present them with memorable images."
