Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource Scripts
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915074059272192 |
|---|---|
| author | Sohail, Muhammad Abdullah Masood, Salaar Iqbal, Hamza |
| author_facet | Sohail, Muhammad Abdullah Masood, Salaar Iqbal, Hamza |
| contents | This study investigates the potential of Large Language Models (LLMs), particularly GPT-4o, for Optical Character Recognition (OCR) in low-resource scripts such as Urdu, Albanian, and Tajik, with English serving as a benchmark. Using a meticulously curated dataset of 2,520 images incorporating controlled variations in text length, font size, background color, and blur, the research simulates diverse real-world challenges. Results emphasize the limitations of zero-shot LLM-based OCR, particularly for linguistically complex scripts, highlighting the need for annotated datasets and fine-tuned models. This work underscores the urgency of addressing accessibility gaps in text digitization, paving the way for inclusive and robust OCR solutions for underserved languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16119 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource Scripts Sohail, Muhammad Abdullah Masood, Salaar Iqbal, Hamza Machine Learning Computer Vision and Pattern Recognition Image and Video Processing This study investigates the potential of Large Language Models (LLMs), particularly GPT-4o, for Optical Character Recognition (OCR) in low-resource scripts such as Urdu, Albanian, and Tajik, with English serving as a benchmark. Using a meticulously curated dataset of 2,520 images incorporating controlled variations in text length, font size, background color, and blur, the research simulates diverse real-world challenges. Results emphasize the limitations of zero-shot LLM-based OCR, particularly for linguistically complex scripts, highlighting the need for annotated datasets and fine-tuned models. This work underscores the urgency of addressing accessibility gaps in text digitization, paving the way for inclusive and robust OCR solutions for underserved languages. |
| title | Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource Scripts |
| topic | Machine Learning Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2412.16119 |