Automatic analysis of artistic paintings using information-based measures

Highlights：

• We perform a direct comparison between state-of-the-art unsupervised probabilistic and algorithmic information measures to specify each measure’s strengths and weaknesses.

• We show that hidden patterns and relationships present in artistic paintings can be identified by analysing their complexity.

• We show an efficient stylistic descriptor by combining the Normalized Compression and a measure of the paintings’ roughness.

• We propose a new descriptor of the artists’ style, artistic influences, and shared techniques.

• We show that average local complexity describes how each author typically composes and distributes the elements across the canvas and, therefore, how their work is perceived.

• We demonstrate that these measures can serve as useful auxiliary features capable of improving current methodologies in the classification of artistic paintings.