Computer Vision Models to Categorize Art Collections According to the Visual Content: A New Approach to the Abstract Art of Antoni Tàpies

Abstract

This study uses computer vision models, which to some extent simulate the initial stages of human visual perception, to help categorize data in large sets of images of artworks by the artist Antoni Tàpies. The images have been analyzed on the basis of their compositional, chromatic and organizational characteristics, without textual notes, so that the analogies found may take us closer to, and help us to understand, the creator’s original values. The system as programmed can assist the specialist by establishing analogies between different artists or periods using the same criteria.

Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning

“…In their study, a database of seven categories of paintings (Abstract, Baroque, Renaissance, Popart, Expressionism, Impressionism, and Cubism) was used from the Artchive fineart dataset using 70 images from each class. Recently, Rosado [35] employed a BoV implemented using a dense-SIFT method for feature extraction and Probabilistic Latent Semantic Analysis (PLSA) to make an image analysis of 434 digitized images from paintings, drawings, books, and engravings by Antoni Tàpies. In general, we note that using handcrafted engineered features makes it possible to obtain encouraging but not perfect results.…”

Automated Visual Content Analysis (AVCA) in Communication Research: A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models

“…Automated approaches to image analysis have been developed and applied quite recently in a variety of disciplines in the humanities and social sciences. Art historians have used computer vision to identify analogies in large samples of art-related images (Rosado, 2017) or to retrieve artworks from an existing database of paintings (Lang & Ommer, 2018). In the social sciences more broadly, for example, a study has employed computer vision to estimate the size and dynamics of human crowds (Aziz et al, 2018).…”