Historical Printed Ornaments: Dataset and Tasks

TL;DR

This paper introduces a new dataset and benchmarks for analyzing historical printed ornaments using unsupervised computer vision, addressing tasks like clustering, element discovery, and change localization relevant to book historians.

Contribution

It provides the Rey's Ornaments dataset, evaluation benchmarks for three complex tasks, and an analysis of state-of-the-art models' limitations on real historical data.

Findings

Simple methods like k-means outperform complex models on the dataset.

State-of-the-art models face limitations with real historical ornament data.

The dataset offers diverse and representative challenges for historical ornament analysis.

Abstract

This paper aims to develop the study of historical printed ornaments with modern unsupervised computer vision. We highlight three complex tasks that are of critical interest to book historians: clustering, element discovery, and unsupervised change localization. For each of these tasks, we introduce an evaluation benchmark, and we adapt and evaluate state-of-the-art models. Our Rey's Ornaments dataset is designed to be a representative example of a set of ornaments historians would be interested in. It focuses on an XVIIIth century bookseller, Marc-Michel Rey, providing a consistent set of ornaments with a wide diversity and representative challenges. Our results highlight the limitations of state-of-the-art models when faced with real data and show simple baselines such as k-means or congealing can outperform more sophisticated approaches on such data. Our dataset and code can be found at https://printed-ornaments.github.io/.