Document Type
Article
Publication Date
2025
DOI
10.3390/electronics14010005
Publication Title
Electronics
Volume
14
Issue
1
Pages
5 (1-22)
Abstract
The long-standing practice of document-based engineering has resulted in the accumulation of a large number of engineering documents across various industries. Engineering documents, such as 2D drawings, continue to play a significant role in exchanging information and sharing knowledge across multiple engineering processes. However, these documents are often stored in non-digitized formats, such as paper and portable document format (PDF) files, making automation difficult. As digital engineering transforms processes in many industries, digitizing engineering documents presents a crucial challenge that requires advanced methods. This research addresses the problem of automatically extracting textual content from non-digitized legacy engineering documents. We introduced an optical character recognition (OCR) system for text detection and recognition that leverages transformer-based generative deep learning models and transfer learning approaches to enhance text recognition accuracy in engineering documents. The proposed system was evaluated on a dataset collected from ships’ engineering drawings provided by a U.S. agency. Experimental results demonstrated that the proposed transformer-based OCR model significantly outperformed pretrained off-the-shelf OCR models.
Rights
© 2024 by the authors.
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
Data Availability
Article states: "Data are publicly unavailable due to privacy restrictions."
ORCID
0000-0003-2542-5454 (Khallouli), 0000-0002-2466-1212 (Uddin), 0000-0003-0144-9099 (Sousa-Poza), 0000-0003-0091-6986 (Jiang Li), Samuel Kovacic (0000-0002-8772-5957)
Original Publication Citation
Khallouli, W., Uddin, M. S., Sousa-Poza, A., Li, J., & Kovacic, S. (2025). Leveraging transformer-based OCR model with generative data augmentation for engineering document recognition. Electronics, 14(1), 1-22, Article 5. https://doi.org/10.3390/electronics14010005
Repository Citation
Khallouli, Wael; Uddin, Mohammad Shahab; Sousa-Poza, Andres; Li, Jiang; and Kovacic, Samuel, "Leveraging Transformer-Based OCR Model with Generative Data" (2025). Engineering Management & Systems Engineering Faculty Publications. 222.
https://digitalcommons.odu.edu/emse_fac_pubs/222
Included in
Artificial Intelligence and Robotics Commons, Scholarly Publishing Commons, Systems Engineering Commons