2025/10/02 by Rixin Zhou, Zhou, Rixin, Qian Zhang +6
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Bronze #Character (mathematics) #Character recognition #Computer Vision and Pattern Recognition (cs.CV) #Cultural heritage #Encoder #FOS: Computer and information sciences #Forensic and Genetic Research #Geophysical Methods and Applications #Handwritten Text Recognition Techniques #Pipeline (software)
paper · pdf · doi:10.48550/arxiv.2510.01651
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Bronze inscriptions (BI), engraved on ritual vessels, constitute a crucial stage of early Chinese writing and provide indispensable evidence for archaeological and historical studies. However, automatic BI recognition remains difficult due to severe visual degradation, multi-domain variability across photographs, rubbings, and tracings, and an extremely long-tailed character distribution. To address these challenges, we curate a large-scale BI dataset comprising 22454 full-page images and 198598 annotated characters spanning 6658 unique categories, enabling robust cross-domain evaluation. Building on this resource, we develop a two-stage detection-recognition pipeline that first localizes inscriptions and then transcribes individual characters. To handle heterogeneous domains and rare classes, we equip the pipeline with LadderMoE, which augments a pretrained CLIP encoder with ladder-style MoE adapters, enabling dynamic expert specialization and stronger robustness. Comprehensive experiments on single-character and full-page recognition tasks demonstrate that our method substantially outperforms state-of-the-art scene text recognition baselines, achieving superior accuracy across head, mid, and tail categories as well as all acquisition modalities. These results establish a strong foundation for bronze inscription recognition and downstream archaeological analysis.