Good Thinking

Proposed rating system would indicate how much photos have been retouched

Proposed rating system would indicate how much photos have been retouched
On a scale of 1 to 5, how much retouching would you say was applied to the left-hand image of Kim Cattrall, to arrive at the vision of loveliness on the right?
View 1 Image
1/1
On a scale of 1 to 5, how much retouching would you say was applied to the left-hand image of Kim Cattrall, to arrive at the vision of loveliness on the right?

Even though we know that the photos we see of models and celebrities are retouched, many of us nonetheless can't help but think "Yeah, but even without that little bit of airbrushing, that person still looks way better than me." For most people, such thoughts are merely a little bit humbling. For others, however, they can lead to Body Dysmorphic Disorder, eating disorders, or severely-low self-esteem - all of which can in turn have very serious consequences, including death. Perhaps if those people knew just how retouched that one photo of Mila Kunis or Ryan Gosling was, however, they might realize how much of a lie it really represented. That's why researchers at New Hampshire's Dartmouth College are proposing a system that objectively assesses the extent of changes made to a photograph, then displays that amount as a number rating on the published photo.

Dartmouth Computer Science Professor Hany Farid and PhD student Eric Kee have created a basic version of the system, which applies a mathematical model to differences between digital "before" and "after" photographs of people. These differences could include changes made via cropping, color adjustment, the slimming or shaping of body parts, the adjustment of facial symmetry, and the removal of features such as wrinkles, blemishes or bags under the eyes.

A number ranging from 1 to 5 is then assigned to each photo, indicating the degree to which it has been altered. In order to check the validity of their system, Farid and Kee got a group of volunteers to compare and rank the differences in hundreds of pairs of before-and-after retouched photographs. The average numbers arrived at by those human test subjects correlated strongly with those generated by the model, for the same images.

The idea is that ultimately, advertisers and other media outlets would be required to display these numbers on their retouched images, so that everyone would know just how unattainable of an ideal was being depicted. According to a report in New Scientist, the Dartmouth system could also be installed as a Photoshop plug-in, which would warn retouchers when they were deviating too far from the original image.