The Artistic Reincarnation Behind the Average Face: Unraveling the Mystery of the Artist’s Face

2023

Teamwork: Yue Zhu, Xiaotong Qiu
Advisor: Xiaochen Hu, Tianyi Chen

Award:

Silver Award of 2023 Singapore Art Design Competition
09/2023

Media

💽 22 Selected Artificial Intelligence Algorithmic Artworks of 2023 | MANA
🖼 Global New Media Art Overview, April 2023 | MANA

Contribution:

Led the project, conceptualization, design and development (p5.js, runway ml platform, osc protocol)

Is our existence the mean of population?

The concept of regression toward the mean was originally derived from the “regression phenomenon” of quantitative traits in organisms discovered by Francis Galton in his study of parent-child relationships in human height, whereby the phenotypic values of the offspring are, on average, closer to the population mean than those of the parents. He measured the heights of 930 adult children and their parents and calculated the average of the parents’ heights. He found that when the average height of the parents was higher than the population average, the children tended to be shorter than their parents. Galton called this phenomenon regression to the mean.

We think ourselves are the unique presence, yet always find ourselves in others, which can be thought of in a way as another kind of regression to the mean in population. So is our existence the mean of the group? Take the group of artists as an example, we construct a database based on artist faces collected from social media such as Linkedin, synthesize the average artist face using StyleGAN, and use Runway’s pre-trained Face Landmarks detection model to analyze the facial phenotypic features of the average face, and use the OSC protocol to communicate with Processing , realizing the real-time incoming audience face data from the camera, and calculating the similarity with the artist average face and the face abstract pattern through the Euclidean distance between the coordinate points.