OBD-Finder: Explainable Coarse-to-Fine Text-Centric Oracle Bone Duplicates Discovery
Journal:
arXiv
Published Date:
May 4, 2025
Abstract
Oracle Bone Inscription (OBI) is the earliest systematic writing system in
China, while the identification of Oracle Bone (OB) duplicates is a fundamental
issue in OBI research. 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 approach with state-of-the-art content-based image retrieval and
image matching methods, showing that our approach 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 OBI researchers for decades. The
models, video illustration and demonstration of this work are available at:
https://github.com/cszhangLMU/OBD-Finder/.
