By mining a vast database of high-school yearbook photos, a machine-vision algorithm reveals the change in hairstyles, clothing, and even smiles over the last century.
Shiry Ginosar at the University of California, Berkeley, and a few others started with a database of American high-school yearbook photographs dating back to 1905. These yearbook photos have been digitized on large scale by local libraries across the U.S. and show full frontal photos of individuals in a standard pose.
They downloaded over 150,000 of these portraits and removed those that were not full frontal portraits, leaving them with 37,000 images from more than 800 yearbooks from 26 U.S. states.
They then grouped the portraits by decade and superimposed the images to produce an “average” face for each period. The image above shows these averages for each decade for men and women. Today's students appear to be more cheerful than their ancestors.
Full story: MIT Technology Review