Ddvr-net improves recognition of damaged historical documents
DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition
Computer Vision and Pattern Recognition
Summary
Historical documents often suffer from damage like faded ink and torn pages, making them hard for computers to read accurately. The authors propose DDVR-Net, a new method that separates the original characters from their damaged appearances and estimates how visible each character is. This helps restore unclear characters while keeping clear ones unchanged. Their work includes a new multilingual dataset and shows better results on different languages and reading styles than existing methods.
What this means in practice
- •For digitization teams: Improve text extraction from damaged historical documents in Tibetan, Mongolian, and Uyghur scripts using a visibility-aware restoration method.
- •For cultural heritage preservation teams: Enhance digital archives by restoring degraded text in low-resource language documents with consistent accuracy across diverse reading orders.
Authors
Jiu Sha, Yu Weng, Mengxiao Zhu
Abstract
Historical document analysis is crucial for cultural heritage preservation and low-resource language digitization. However, real historical documents often suffer from severe degradation, such as ink erosion and structural damage, causing mixed-visibility character sequences. Conventional OCR systems struggle in such evidence-limited scenarios, while contextual language models may over-correct visually clear characters. To address these challenges, we propose DDVR-Net, a degradation-aware decoupling and visibility-guided restoration framework for historical document recognition. DDVR-Net decouples intrinsic glyph structures from physical corruption at the feature level and predicts local visibility to estimate character reliability. A contextual decoder is selectively activated through a visibility-guided gate, restoring degraded characters while preserving clear visual recognition. Furthermore, we construct a low-resource multilingual benchmark covering Tibetan, Mongolian, and Uyghur scripts with 187000 document pairs, combining large-scale synthetic data and progressive training with real-world annotations to reduce the synthetic-to-real gap. Extensive experiments demonstrate that DDVR-Net consistently outperforms existing methods across three languages and diverse reading orders, providing an effective framework and benchmark for low-resource historical document recognition. Code and Benchmark: https://github.com/Shajiu/DDVR-Net