Data-Driven Enhancement of Facial Attractiveness (SIGGRAPH 2008)

Video Description: Video illustrating the SIGGRAPH 2008 paper by Tommer Leyvand, Daniel Cohen-Or, Gideon Dror and Dani Lischinski. A data-driven approach to the challenging problem of enhancing the aesthetic appeal (or the attractiveness) of human faces in frontal photographs (portraits), while maintaining close similarity with the original.
 

The “beautification engine” is a new computer program that uses a mathematical formula to alter the original form into a theoretically more attractive version, while maintaining what programmers call an “unmistakable similarity” to the original.

The software program, developed by computer scientists in Israel, is based on the responses of 68 men and women, age 25 to 40, from Israel and Germany, who viewed photographs of white male and female faces and picked the most attractive ones.

Scientists took the data and applied an algorithm involving 234 measurements between facial features, including the distances between lips and chin, the forehead and the eyes, or between the eyes.

The research, published in the August proceedings of SIGGRAPH 2008, an annual conference on computer graphics, is one of the latest studies in a growing field that merges beauty and science, a subject that has drawn mounting interest in academia in the last decade. Studies have shown that there is surprising agreement about what makes a face attractive. Symmetry is at the core, along with youthfulness; clarity or smoothness of skin; and vivid color, say, in the eyes and hair. There is little dissent among people of different cultures, ethnicities, races, ages and gender. Read more at: New York Times by Sarah Kershaw, October 8, 2008.