A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mustafa, Ahmed, Rafique, Muhammad Tahir, Baig, Muhammad Ijlal, Sajid, Hasan, Khan, Muhammad Jawad, Kallu, Karam Dad
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913486130380800
author Mustafa, Ahmed
Rafique, Muhammad Tahir
Baig, Muhammad Ijlal
Sajid, Hasan
Khan, Muhammad Jawad
Kallu, Karam Dad
author_facet Mustafa, Ahmed
Rafique, Muhammad Tahir
Baig, Muhammad Ijlal
Sajid, Hasan
Khan, Muhammad Jawad
Kallu, Karam Dad
contents This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures and attention mechanisms to address the distinct challenges of Urdu script recognition, including its diverse text styles, fonts, and variations. The model employs a permuted autoregressive sequence (PARSeq) architecture, which enhances its performance by enabling context-aware inference and iterative refinement through the training of multiple token permutations. This method allows the model to adeptly manage character reordering and overlapping characters, commonly encountered in Urdu script. Trained on a dataset comprising approximately 160,000 Urdu text images, the model demonstrates a high level of accuracy in capturing the intricacies of Urdu script, achieving a CER of 0.178. Despite ongoing challenges in handling certain text variations, the model exhibits superior accuracy and effectiveness in practical applications. Future work will focus on refining the model through advanced data augmentation techniques and the integration of context-aware language models to further enhance its performance and robustness in Urdu text recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text
Mustafa, Ahmed
Rafique, Muhammad Tahir
Baig, Muhammad Ijlal
Sajid, Hasan
Khan, Muhammad Jawad
Kallu, Karam Dad
Computer Vision and Pattern Recognition
Artificial Intelligence
This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures and attention mechanisms to address the distinct challenges of Urdu script recognition, including its diverse text styles, fonts, and variations. The model employs a permuted autoregressive sequence (PARSeq) architecture, which enhances its performance by enabling context-aware inference and iterative refinement through the training of multiple token permutations. This method allows the model to adeptly manage character reordering and overlapping characters, commonly encountered in Urdu script. Trained on a dataset comprising approximately 160,000 Urdu text images, the model demonstrates a high level of accuracy in capturing the intricacies of Urdu script, achieving a CER of 0.178. Despite ongoing challenges in handling certain text variations, the model exhibits superior accuracy and effectiveness in practical applications. Future work will focus on refining the model through advanced data augmentation techniques and the integration of context-aware language models to further enhance its performance and robustness in Urdu text recognition.
title A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.15119