Automatic analysis of artistic paintings using information-based measures. (June 2021)

• Record Type: Journal Article
• Authors: Silva, Jorge Miguel; Pratas, Diogo; Antunes, Rui; Matos, Sérgio; Pinho, Armando J.
• Is Part Of: Pattern recognition. Volume 114(2021)
• Publication Date: 2021-06
• Subjects: Image analysis -- Data compression -- BDM -- Artistic paintings -- Algorithmic information theory; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.107864
• Languages: English
• ISSNs: 0031-3203

Abstract

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. Abstract: The artistic community is increasingly relying on automatic computational analysis for authentication and classification of artistic paintings. In this paper, we identify hidden patterns and relationships present in artistic paintings by analysing their complexity, a measure that quantifies the sum of characteristics of an object. Specifically, we apply Normalized Compression (NC) and the Block Decomposition Method (BDM) to a dataset of 4, 266 paintings from 91 authors and examine the potential of these information-based measures as descriptors of artistic paintings. Both measures consistently described the equivalent types of paintings, authors, and artistic movements. Moreover, combining the NC with a measure of the roughness of the paintings creates an efficient stylistic descriptor. Furthermore, by quantifying the local information of each painting, we define a fingerprint that describes critical information regarding the artists' style, their artistic influences, and shared techniques. More fundamentally, this information describes how each author typically composes and distributes the elements across the canvas and, therefore, how their work is perceived. Finally, we demonstrate that regional complexity and two-point height difference correlation function are useful auxiliary features that improve current methodologies in style and author classification of artistic paintings. The whole study is supported by an extensive website (http://panther.web.ua.pt ) for fast author characterization and authentication.