You can now determine the memorability of photos, thanks to new MIT software
MIT is experimenting with the color and exposure of photos, and no, it’s not for another selfie filter.
Researchers at the university are developing a software that can predict how well people will remember certain images with “near human accuracy,’’ according to BetaBoston.
LaMem is the largest annotated image memorability data-set to date, containing 60,000 images , according the system’s site.
Anyone can feed images into the database, which are then overlaid with a heat map to show regions of the photo viewers are most likely to remember. Warm colors are more memorable sections, and cooler colors show portions less likely to stick with someone, BetaBoston reported. The images are then assigned a memorability score.
A graduate student on the project told BetaBoston that the technology could be used to make advertisements more effective, and make photos trigger stronger emotions.
Read the full story on BetaBoston.
To comment, please create a screen name in your profile
To comment, please verify your email address
Conversation
This discussion has ended. Please join elsewhere on Boston.com