AVERAGE ART
<p><strong>TLDR:</strong> I took a subset of 18.5K portraits from a dataset of the Kaggle competition, <a href="https://www.kaggle.com/c/painter-by-numbers/data" rel="noopener ugc nofollow" target="_blank">Painter by Numbers</a>, and arranged them by style and gender. Then I used the <a href="https://github.com/johnwmillr/Facer" rel="noopener ugc nofollow" target="_blank">Facer library from John W. Miller</a> to build average faces based on these portrait groups, as well as a time-lapse of average faces from the portraits dating from the Middle Ages to the 20th century. Check out <a href="https://society6.com/altsoph/collection/average-art" rel="noopener ugc nofollow" target="_blank">my society6 page</a> for prints of these portraits.</p>
<h1>Details</h1>
<p>I used metadata from the <a href="https://www.kaggle.com/c/painter-by-numbers/data" rel="noopener ugc nofollow" target="_blank">Painter by Numbers dataset</a>, where the subset of portraits was less than 20%. The metadata is quite detailed and convenient, including authors, styles, titles, and years of creation. After filtering, I had about 18.5K paintings declared as portraits. However, my attempts to build average faces by artistic style without additional data cleaning produced strange sexless faces.</p>
<p>Therefore, I had to break these portraits down into categories: group, male, female, child, and other portraits. The “other” portraits were those where I wasn’t able to determine the character’s gender, e.g. some of the Cubist paintings. Note: This creates a bias towards more human-like faces, which is more significant for abstract types of art.</p>
<p><a href="https://medium.com/altsoph/average-art-a917340cd7fa"><strong>Click Here</strong></a></p>