OmniOCR: Generalist OCR for Ethnic Minority Languages
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912923356495872 |
|---|---|
| author | Liu, Bonan Zhang, Zeyu Meng, Bingbing Wang, Han Zhang, Hanshuo Wang, Chengping Ergu, Daji Cai, Ying |
| author_facet | Liu, Bonan Zhang, Zeyu Meng, Bingbing Wang, Han Zhang, Hanshuo Wang, Chengping Ergu, Daji Cai, Ying |
| contents | Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21042 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OmniOCR: Generalist OCR for Ethnic Minority Languages Liu, Bonan Zhang, Zeyu Meng, Bingbing Wang, Han Zhang, Hanshuo Wang, Chengping Ergu, Daji Cai, Ying Computer Vision and Pattern Recognition Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR. |
| title | OmniOCR: Generalist OCR for Ethnic Minority Languages |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.21042 |