What makes a Pollock Pollock: a machine vision approach

Abstract

Jackson Pollock introduced a revolutionary artistic style of dripping paint on a horizontal canvas. Here we study Pollock's unique artistic style by using computational methods for characterizing the low-level numerical differences between original Pollock drip paintings and drip paintings of other painters who attempted to mimic his signature drip painting style. Four thousands and twenty four numerical image content descriptors were extracted from each painting, and compared using Weighted Nearest Neighbor classification such that the Fisher discriminant scores of the content descriptors were used as weights. In 93% of the cases the computer analysis was able to differentiate between an original and a non-original Pollock drip painting. The most discriminative image content descriptors that were unique to the work of Pollock were the fractal features, but other numerical image content descriptors such as Zernike polynomials, Haralick textures, and Chebyshev statistics show substantial differences between original and non-original Pollock drip paintings. These experiments show that the uniqueness of Pollock's drip painting style is not reflected merely by fractals, but also by other numerical image content descriptors that reflect the visual content. The code and software used for the experiment is publicly available, and can be used to study the work of other artists.

Computational and Experimental Approaches to Visual Aesthetics

“…Stork ( 2009b ) later defended Taylor and colleagues and argued that, while one feature in isolation may not be sufficient for the analysis, a combination of multiple fractal measures can provide useful information. Shamir ( 2015 ) used a set of features from biological image analysis (Shamir et al, 2008 ) and reported an accuracy of 93.0% in discriminating between original and non-original drip paintings.…”

Computer Analysis of Architecture Using Automatic Image Understanding

“…For instance, it showed that the computer analysis of art is largely in agreement with how art historians view influential links between different schools of European art (Shamir & Tarakhovsky, 2012). It was also used to identify features typical to Jackson Pollock (Shamir, 2015) and show evidence of mathematical similarities between Jackson Pollock and Vincent von Gogh (Shamir, 2012). Another use of the Wndchrm scheme related to automatic analysis of art is the studying of art perception, showing patterns of differences between abstract expressionism and paintings by children and animals (Shamir et al, 2016).…”

Predicting and grouping digitized paintings by style using unsupervised feature learning

“…Thus, we have introduced a method to capture the stylistic characteristics of art in an objective manner. This greatly simplifies the feature extraction process in art, as it has been indicated by Shamir (14,50,51) that a great variety of handcrafted features are necessary to successfully capture the characteristics of art. Our success is due to that fact that we utilized the recently proposed UFLK algorithm (31,38,52), which facilitates the use of a deep learning-like algorithm.…”