# Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach

arXiv: https://arxiv.org/abs/1908.10254 · HTML: https://mlsanity.com/paper/1908.10254/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Diffusion Models as Data Mining Tools](https://mlsanity.com/paper/2408.02752/) (2024)
- [Object Retrieval and Localization in Large Art Collections using Deep Multi-Style Feature Fusion and Iterative Voting](https://mlsanity.com/paper/2107.06935/) (2021)
- [Image Collation: Matching illustrations in manuscripts](https://mlsanity.com/paper/2108.08109/) (2021)
- [Npix2Cpix: A GAN-Based Image-to-Image Translation Network With Retrieval- Classification Integration for Watermark Retrieval From Historical Document Images](https://mlsanity.com/paper/2406.03556/) (2024)
- [ArcAid: Analysis of Archaeological Artifacts using Drawings](https://mlsanity.com/paper/2211.09480/) (2022)
- [Rooms with Text: A Dataset for Overlaying Text Detection](https://mlsanity.com/paper/2211.11350/) (2022)

## Abstract (arXiv)

Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians. With a large number of well-defined classes, cluttered and noisy samples, different types of representations, both subtle differences between classes and high intra-class variation, historical watermarks are also challenging for pattern recognition. In this paper, overcoming the difficulty of data collection, we present a large public dataset with more than 6k new photographs, allowing for the first time to tackle at scale the scenarios of practical interest for scholars: one-shot instance recognition and cross-domain one-shot instance recognition amongst more than 16k fine-grained classes. We demonstrate that this new dataset is large enough to train modern deep learning approaches, and show that standard methods can be improved considerably by using mid-level deep features. More precisely, we design both a matching score and a feature fine-tuning strategy based on filtering local matches using spatial consistency. This consistency-based approach provides important performance boost compared to strong baselines. Our model achieves 55% top-1 accuracy on our very challenging 16,753-class one-shot cross-domain recognition task, each class described by a single drawing from the classic Briquet catalog. In addition to watermark classification, we show our approach provides promising results on fine-grained sketch-based image retrieval.