WE ALL know that pictures of models and celebrities are given a little digital 鈥渆nhancement鈥� before they appear on magazine covers.
Well now you too could enjoy such treatment: an algorithm has been developed that morphs photographs of human faces into subtly more attractive versions of themselves. By making tiny adjustments to the distances between hundreds of different facial features, the 鈥渄igital beautification鈥� algorithm is designed to make a face more attractive in just a few minutes without significantly altering the person鈥檚 appearance.
The system, created by Tommer Leyvand of Tel Aviv University in Israel, could not only give magazine editors and advertisers a new photographic tool, it could also help amateur photographers touch up their digital images at home.
Advertisement
In 2005 a team led by Leyvand鈥檚 colleague Yael Eisenthal asked people to rate the attractiveness of faces in almost 200 photographs. Software then analysed the images, measuring distances between facial features and ratios such as that between facial width at eye and mouth level, and the thickness of the eyebrows. It compared these with the attractiveness ratings given by the volunteers to create a set of rules, known as the 鈥渂eauty function鈥�, for assessing whether a face is attractive.
Leyvand has now written a second piece of software that applies this algorithm to a facial image to make adjustments to features so that they more closely obey the rules. It then analyses the results to determine which changes have been successful, and discard any that don鈥檛 work. Users can also adjust the severity of the changes.
When Leyvand showed 40 people before and after shots of a selection of faces, 79 per cent said the changes made the person more attractive. Leyvand presented his work on 3 August at the SIGGRAPH conference in Boston.
