Printed document layout analysis and optical character recognition system based on deep learning

Abstract This paper proposes a layout analysis and text recognition system for printed documents based on deep learning. Initially, scanned documents or image files are processed using a layout analysis algorithm based on YOLOv4 and YOLOv8 deep learning to identify the positions of titles, text para...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong-Lin Li, Shih-Kai Lee, Yin-Ting Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07439-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334713350619136
author Dong-Lin Li
Shih-Kai Lee
Yin-Ting Liu
author_facet Dong-Lin Li
Shih-Kai Lee
Yin-Ting Liu
author_sort Dong-Lin Li
collection DOAJ
description Abstract This paper proposes a layout analysis and text recognition system for printed documents based on deep learning. Initially, scanned documents or image files are processed using a layout analysis algorithm based on YOLOv4 and YOLOv8 deep learning to identify the positions of titles, text paragraphs, tables, and images within the document. Each of these categories undergoes specific character segmentation processing. Then, the content is recognized using a text recognition algorithm based on Convolutional Neural Networks (CNN). Finally, the recognized text is integrated and output in editable formats, such as JSON or Microsoft formats. Our proposed method enables convenient, fast, and highly accurate OCR processing on a local computer.
format Article
id doaj-art-abfed52ebf9c4ae6a2b0e64ab4341edd
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-abfed52ebf9c4ae6a2b0e64ab4341edd2025-08-20T03:45:30ZengNature PortfolioScientific Reports2045-23222025-07-0115111510.1038/s41598-025-07439-yPrinted document layout analysis and optical character recognition system based on deep learningDong-Lin Li0Shih-Kai Lee1Yin-Ting Liu2Department of electrical engineering, National Taiwan Ocean UniversityDepartment of electrical engineering, National Taiwan Ocean UniversityDepartment of electrical engineering, National Taiwan Ocean UniversityAbstract This paper proposes a layout analysis and text recognition system for printed documents based on deep learning. Initially, scanned documents or image files are processed using a layout analysis algorithm based on YOLOv4 and YOLOv8 deep learning to identify the positions of titles, text paragraphs, tables, and images within the document. Each of these categories undergoes specific character segmentation processing. Then, the content is recognized using a text recognition algorithm based on Convolutional Neural Networks (CNN). Finally, the recognized text is integrated and output in editable formats, such as JSON or Microsoft formats. Our proposed method enables convenient, fast, and highly accurate OCR processing on a local computer.https://doi.org/10.1038/s41598-025-07439-yOCRLayout analysisCNNYOLODeep learning
spellingShingle Dong-Lin Li
Shih-Kai Lee
Yin-Ting Liu
Printed document layout analysis and optical character recognition system based on deep learning
Scientific Reports
OCR
Layout analysis
CNN
YOLO
Deep learning
title Printed document layout analysis and optical character recognition system based on deep learning
title_full Printed document layout analysis and optical character recognition system based on deep learning
title_fullStr Printed document layout analysis and optical character recognition system based on deep learning
title_full_unstemmed Printed document layout analysis and optical character recognition system based on deep learning
title_short Printed document layout analysis and optical character recognition system based on deep learning
title_sort printed document layout analysis and optical character recognition system based on deep learning
topic OCR
Layout analysis
CNN
YOLO
Deep learning
url https://doi.org/10.1038/s41598-025-07439-y
work_keys_str_mv AT donglinli printeddocumentlayoutanalysisandopticalcharacterrecognitionsystembasedondeeplearning
AT shihkailee printeddocumentlayoutanalysisandopticalcharacterrecognitionsystembasedondeeplearning
AT yintingliu printeddocumentlayoutanalysisandopticalcharacterrecognitionsystembasedondeeplearning