A Data Set and a Convolutional Model for Iconography Classification in Paintings

Abstract

Iconography in art is the discipline that studies the visual content of artworks to determine their motifs and themes and to characterize the way these are represented. It is a subject of active research for a variety of purposes, including the interpretation of meaning, the investigation of the origin and diffusion in time and space of representations, and the study of influences across artists and art works. With the proliferation of digital archives of art images, the possibility arises of applying Computer Vision techniques to the analysis of art images at an unprecedented scale, which may support iconography research and education. In this paper we introduce a novel paintings data set for iconography classification and present the quantitative and qualitative results of applying a Convolutional Neural Network (CNN) classifier to the recognition of the iconography of artworks. The proposed classifier achieves good performances (71.17% Precision, 70.89% Recall, 70.25% F1-Score and 72.73% Average Precision) in the task of identifying saints in Christian religious paintings, a task made difficult by the presence of classes with very similar visual features. Qualitative analysis of the results shows that the CNN focuses on the traditional iconic motifs that characterize the representation of each saint and exploits such hints to attain correct identification. The ultimate goal of our work is to enable the automatic extraction, decomposition, and comparison of iconography elements to support iconographic studies and automatic art work annotation.

Understanding and Creating Art with AI: Review and Outlook

“…A comprehensive overview of the current work related to classification of artworks, as well as an approach towards classifying artworks based on iconographic elements is presented in [94].…”

Transfer Learning for the Visual Arts: The Multi-modal Retrieval of Iconclass Codes

“…Deep learning [26,44] increasingly attracts the attention of scholars from the cultural heritage domain, due to its state-of-the-art performance across multiple real-world problems [17]. Iconclass has already drawn attention of the scientiic community in the following tasks: neural machine translation [2], image classiication [31], object detection [36], image captioning [7,8], and information retrieval [3]. In this work, we aim to automate the assignment of Iconclass codes using the latest advances in deep learning.…”

“…Deep learning (or machine learning) ofers several general ways to tackle this problem: classiication, object detection, and information retrieval. In classiication, a model aims to predict an Iconclass code of an object from a set of predeined concepts, based on a visual reproduction of an artwork [31] and/or textual metadata. In addition to the prediction of the Iconclass codes, an object detector can be trained to ind the bounding box of a concept in an image [36].…”