ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition
PLOS ONE · 17.05.2024 · 19 (5) · e0302590
DOI: 10.1371/journal.pone.0302590 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 17.05.2024. Verfasst von Ameer Hamza und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Engineering, Central South University, Changsha, China. Hauptthemen laut MEDLINE: Handwriting, Deep Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Automatic Urdu handwritten text recognition is a challenging task in the OCR industry. Unlike printed text, Urdu handwriting lacks a uniform font and structure. This lack of uniformity causes data inconsistencies and recognition issues. Different writing styles, cursive scripts, and limited data make Urdu text recognition a complicated task. Major languages, such as English, have experienced advances in automated recognition, whereas low-resource languages, such as Urdu, still lag. Transformer-based models are promising for automated recognition in high- and low-resource languages such as Urdu. This paper presents a transformer-based method called ET-Network that integrates self-attention into EfficientNet for feature extraction and a transformer for language modeling. The use of self-attention layers in EfficientNet helps to extract global and local features that capture long-range dependencies. These features proceeded into a vanilla transformer to generate text, and a prefix beam search is used for the finest outcome. NUST-UHWR, UPTI2.0, and MMU-OCR-21 are three datasets used to train and test the ET Network for a handwritten Urdu script. The ET-Network improved the character error rate by 4% and the word error rate by 1.55%, while establishing a new state-of-the-art character error rate of 5.27% and a word error rate of 19.09% for Urdu handwritten text.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Computer Science and Engineering, Central South University, Changsha, China.
ORCID-Profile: Ameer Hamza, Shengbing Ren, Usman Saeed
Zitieren
APA
Hamza, A., Ren, S., & Saeed, U. (2024). ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition. PLOS ONE, 19(5), e0302590. https://doi.org/10.1371/journal.pone.0302590
Vancouver
Hamza A, Ren S, Saeed U. ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition. PLOS ONE. 2024;19(5):e0302590. doi:10.1371/journal.pone.0302590
BibTeX
@article{Hamza2024,
author = {Hamza, Ameer and Ren, Shengbing and Saeed, Usman},
title = {ET-Network: A novel efficient transformer deep learning model for automated Urdu handwritten text recognition},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {5},
pages = {e0302590},
doi = {10.1371/journal.pone.0302590}
}
EUVIMED