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.
@article{arxiv.2412.16119,
title = {Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource Scripts},
author = {Muhammad Abdullah Sohail and Salaar Masood and Hamza Iqbal},
journal= {arXiv preprint arXiv:2412.16119},
year = {2024}
}