用度量学习提升古埃及象形文字识别，准确率达97.7%。
The OCR-PT-CT Project: Semi-Automatic Recognition of Ancient Egyptian Hieroglyphs Based on Metric Learning
- 基于度量学习构建识别模型，适应小样本新符号。
- 在140类象形文字上达到97.7%准确率，优于传统方法。
- 适合考古学家与数字人文研究者使用，支持数据共享。
数字人文正深刻改变埃及学研究方式。OCR-PT-CT项目提出一种基于图像的象形文字识别方法，针对阿德里安·德·巴克（1935–1961）编纂的棺文（CT）及詹姆斯·艾伦（2006）整理的中王国时期金字塔文（PT）。系统可识别象形文字并转写为加丁纳编码（Gardiner's codes）。通过网络工具按咒语与文献来源组织结果，数据以CSV格式存储，便于集成至MORTEXVAR数据集（含元数据、转写与翻译）。识别方案包括：训练于140类象形文字的MobileNet网络达93.87%准确率，但对少数类表现差；新提出的深度度量学习方法在类别不平衡下表现更优，准确率达97.70%，识别更多符号。因性能更优且适应性强，最终系统采用度量学习作为默认分类器。
原文摘要 · Abstract (English)
Digital humanities are significantly transforming how Egyptologists study ancient Egyptian texts. The OCR-PT-CT project proposes a recognition method for hieroglyphs based on images of Coffin Texts (CT) from Adriaan de Buck (1935-1961) and Pyramid Texts (PT) from Middle Kingdom coffins (James Allen, 2006). The system identifies hieroglyphs and transcribes them into Gardiner's codes. A web tool organizes them by spells and witnesses, storing the data in CSV format for integration with the MORTEXVAR dataset, which collects Coffin Texts with metadata, transliterations, and translations for research. Recognition has been addressed in two ways: a Mobilenet neural network trained on 140 hieroglyph classes achieved 93.87 \% accuracy but struggled with underrepresented classes. A novel Deep Metric Learning approach improves flexibility for new or data-limited signs, achieving 97.70 \% accuracy and recognizing more hieroglyphs. Due to its superior performance under class imbalance and adaptability, the final system adopts Deep Metric Learning as the default classifier.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。