Researchers say they have created a quantitative way to assess “creativity” in works of art that they argue comes close to a scholarly assessment. Ahmed Elgammal and Babak Saleh (The Art and Artificial Intelligence Laboratory, Department of Computer Science, Rutgers University) used 1,710 paintings available on Artchive.com and ran them through their algorithm that looked at qualities such as texture, color, lines, movement, harmony, and balance. The algorithm then “measures the originality and influence of artworks by using sophisticated visual analysis to compare each piece to older and newer artwork…from the premise that the most creative art was that which broke most from the past, and then inspired the greatest visual shifts in the works that followed.”
via Quartz