Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912737389445120 |
|---|---|
| author | Nguyen, Minh Hoang Thiet, Su Nguyen |
| author_facet | Nguyen, Minh Hoang Thiet, Su Nguyen |
| contents | Recognizing and processing Classical Chinese (Han-Nom) texts play a vital role in digitizing Vietnamese historical documents and enabling cross-lingual semantic research. However, existing OCR systems struggle with degraded scans, non-standard glyphs, and handwriting variations common in ancient sources. In this work, we propose a fine-tuning approach for PaddleOCRv5 to improve character recognition on Han-Nom texts. We retrain the text recognition module using a curated subset of ancient Vietnamese Chinese manuscripts, supported by a full training pipeline covering preprocessing, LMDB conversion, evaluation, and visualization. Experimental results show a significant improvement over the base model, with exact accuracy increasing from 37.5 percent to 50.0 percent, particularly under noisy image conditions. Furthermore, we develop an interactive demo that visually compares pre- and post-fine-tuning recognition results, facilitating downstream applications such as Han-Vietnamese semantic alignment, machine translation, and historical linguistics research. The demo is available at https://huggingface.co/spaces/MinhDS/Fine-tuned-PaddleOCRv5 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5 Nguyen, Minh Hoang Thiet, Su Nguyen Computer Vision and Pattern Recognition Computation and Language 68T50, 68T50, 68T10 I.2.7; I.5; I.7.5 Recognizing and processing Classical Chinese (Han-Nom) texts play a vital role in digitizing Vietnamese historical documents and enabling cross-lingual semantic research. However, existing OCR systems struggle with degraded scans, non-standard glyphs, and handwriting variations common in ancient sources. In this work, we propose a fine-tuning approach for PaddleOCRv5 to improve character recognition on Han-Nom texts. We retrain the text recognition module using a curated subset of ancient Vietnamese Chinese manuscripts, supported by a full training pipeline covering preprocessing, LMDB conversion, evaluation, and visualization. Experimental results show a significant improvement over the base model, with exact accuracy increasing from 37.5 percent to 50.0 percent, particularly under noisy image conditions. Furthermore, we develop an interactive demo that visually compares pre- and post-fine-tuning recognition results, facilitating downstream applications such as Han-Vietnamese semantic alignment, machine translation, and historical linguistics research. The demo is available at https://huggingface.co/spaces/MinhDS/Fine-tuned-PaddleOCRv5 |
| title | Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5 |
| topic | Computer Vision and Pattern Recognition Computation and Language 68T50, 68T50, 68T10 I.2.7; I.5; I.7.5 |
| url | https://arxiv.org/abs/2510.04003 |