Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery

TL;DR

This paper presents a progressive framework combining image keypoints and text content analysis to identify ancient manuscript duplicates, achieving high accuracy and efficiency, and discovering new duplicates missed by experts.

Contribution

The work introduces a novel multi-level duplicate discovery method that integrates unsupervised image matching with semantic text analysis, improving detection of ancient manuscript duplicates.

Findings

Comparable recall with state-of-the-art methods

Highest simplified mean reciprocal rank scores

Discovered over 60 new OB duplicate pairs

Abstract

Ancient manuscripts are the primary source of ancient linguistic corpora. However, many ancient manuscripts exhibit duplications due to unintentional repeated publication or deliberate forgery. The Dead Sea Scrolls, for example, include counterfeit fragments, whereas Oracle Bones (OB) contain both republished materials and fabricated specimens. Identifying ancient manuscript duplicates is of great significance for both archaeological curation and ancient history study. In this work, we design a progressive OB duplicate discovery framework that combines unsupervised low-level keypoints matching with high-level text-centric content-based matching to refine and rank the candidate OB duplicates with semantic awareness and interpretability. We compare our model with state-of-the-art content-based image retrieval and image matching methods, showing that our model yields comparable recall performance and the highest simplified mean reciprocal rank scores for both Top-5 and Top-15 retrieval results, and with significantly accelerated computation efficiency. We have discovered over 60 pairs of new OB duplicates in real-world deployment, which were missed by domain experts for decades. Code, model and real-world results are available at: https://github.com/cszhangLMU/OBD-Finder/.