Auto-Perception of Boob and Blemish Enhancement

Eric Keeand Hany Farid created algorithms to detect which portions of a photograph have been monkeyed with, and how much monkeying was done to each portion. Their study is

“A Perceptual Metric for Photo Retouching,” Eric Kee [pictured here — we leave it to you to determine whether the image has been enhanced] and Hany Farid, Proceedings of the National Academy of Sciences, epub November 28, 2011. (Thanks to investigator Gus Rancatore for bringing this to our attention.) The authors, at Dartmouth College, Hanover, New Hampshire, report:

“In recent years, advertisers and magazine editors have been widely criticized for taking digital photo retouching to an extreme. Impossibly thin, tall, and wrinkle- and blemish-free models are routinely splashed onto billboards, advertisements, and magazine covers. The ubiquity of these unrealistic and highly idealized images has been linked to eating disorders and body image dissatisfaction in men, women, and children. In response, several countries have considered legislating the labeling of retouched photos. We describe a quantitative and perceptually meaningful metric of photo retouching. Photographs are rated on the degree to which they have been digitally altered by explicitly modeling and estimating geometric and photometric changes. This metric correlates well with perceptual judgments of photo retouching and can be used to objectively judge by how much a retouched photo has strayed from reality.”

Here’s a detail from the study. It shows an original version of what was transformed into a glamorous image, then the enhanced version, then an indication of where specifically it’s been enhanced (red and yellow indicating the most enhancement, blue the least):

The study contains many other images, some of which you may find illusion-shattering if you are a till-now-happy consumer of popular culture. Key and Farid also have a nice gallery online of before and after images of glittery people.