Automatic Analysis of Human Body Representations in Western Art

TL;DR

This paper presents a computer vision pipeline that analyzes human body representations in paintings, combining pose estimation methods and normalization techniques to reveal artistic trends and variations across periods and artists.

Contribution

It introduces a novel pipeline integrating pose estimation, occlusion handling, and normalization to analyze artistic depictions of the human body.

Findings

Improved analysis of poses over skeleton-based methods

Revealed common and uncommon artist-specific poses

Enhanced visualization of joint articulation in paintings

Abstract

The way the human body is depicted in classical and modern paintings is relevant for art historical analyses. Each artist has certain themes and concerns, resulting in different poses being used more heavily than others. In this paper, we propose a computer vision pipeline to analyse human pose and representations in paintings, which can be used for specific artists or periods. Specifically, we combine two pose estimation approaches (OpenPose and DensePose, respectively) and introduce methods to deal with occlusion and perspective issues. For normalisation, we map the detected poses and contours to Leonardo da Vinci's Vitruvian Man, the classical depiction of body proportions. We propose a visualisation approach for illustrating the articulation of joints in a set of paintings. Combined with a hierarchical clustering of poses, our approach reveals common and uncommon poses used by artists. Our approach improves over purely skeleton based analyses of human body in paintings.