Historical Printed Ornaments: Dataset and Tasks
This work addresses the problem of analyzing historical printed ornaments for book historians, providing a dataset and benchmarks, but it is incremental as it adapts existing methods to a new domain.
The paper tackled the study of historical printed ornaments using unsupervised computer vision, introducing the Rey's Ornaments dataset and benchmarks for clustering, element discovery, and change localization, with results showing that simple baselines like k-means or congealing can outperform state-of-the-art models on this real data.
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/.