用深度学习自动分类古籍扫描页，准确率达99%，助力文献数字化
Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing
- 基于48,000张历史文档图像，用CNN与Transformer模型训练分类器
- 最优模型达99.16%准确率，对超64万张未标注页面实现高效分类
- 适合人文数字项目、古籍处理系统，结果可开源复现
人文领域的大规模文献数字化项目生成海量异构的扫描文档档案，人工整理已不可行。本文提出一种自动化图像分类系统，根据视觉内容类型（文本、表格、图形）对扫描页面进行分类，以支持后续如光学字符识别（OCR）或结构化数据提取等任务。研究基于超过48,000张来自百年历史捷克考古档案的标注图像，经过四轮专家评审标注。先建立基于手工特征的随机森林基线，再对比多种微调后的深度学习架构：卷积神经网络（EfficientNetV2、RegNetY）、视觉与文档图像变换器（ViT、DiT）及多模态CLIP模型。设计了由领域专家共同确定的11类标签体系，并通过五折交叉验证评估。结果显示，基线模型准确率约75%；微调后的CNN与Transformer显著提升性能，其中RegNetY-16GF在测试集上达到99.16%的Top-1准确率，ViT-large为99.12%；优化文本描述的CLIP ViT-B/16也达到99.14%。结论表明，仅使用图像的模型（尤其是RegNetY-16GF）在649,508张未标注档案页面上实现了近90%的模型间一致性，而CLIP在未标注数据上与图像模型的吻合度低于65%，不适宜部署。最终模型、标注数据集与代码均以开源许可公开。
原文摘要 · Abstract (English)
Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale. This work addresses the need for an automated system to classify scanned page images based on visual content type - text, tables, and graphics - enabling content-specific downstream processing such as Optical Character Recognition (OCR) or structured data extraction. Methods: An image classification system was developed and evaluated on a dataset of over 48,000 annotated historical page images from century-old Czech archaeological archives, refined through four successive annotation stages with domain-expert review. A Random Forest Classifier baseline was established using hand-crafted image features. Subsequently, deep learning architectures were fine-tuned and compared: Convolutional Neural Networks (EfficientNetV2, RegNetY), Vision and Document Image Transformers (ViT, DiT), and multimodal CLIP models. An 11-category label scheme was designed collaboratively with domain experts and evaluated via five-fold cross-validation. Results: The feature-based baseline achieved approximately 75% accuracy. Fine-tuned CNNs and Transformers substantially outperformed it, with RegNetY-16GF achieving 99.16% and ViT-large 99.12% Top-1 accuracy on the held-out test set. CLIP ViT-B/16 reached 99.14% with optimized text descriptions. Conclusion: Image-only models, particularly RegNetY-16GF, deliver near-perfect classification accuracy and produce consistent labels across 649,508 unlabeled archival pages with over 90% inter-model agreement. Fine-tuned CLIP, despite competitive test-set accuracy, showed under 65% agreement with image-only models on unlabeled data, making it less suitable for deployment. The final models, annotated dataset, and software are publicly available under open-source licenses.
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。