Salvato in:
Dettagli Bibliografici
Autori principali: Sohail, Muhammad Abdullah, Masood, Salaar, Iqbal, Hamza
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.16119
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_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