TableBorderNet: A Table Border Extraction Network Considering Topological Regularity

Accurate extraction of table borders in scanned road engineering drawings is crucial for the digital transformation of engineering archives, which is an essential step in the development of intelligent infrastructure systems. However, challenges such as degraded borders, image blur, and character ad...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Yang, Shengqiang Zhou, Xialing Li, Yuchun Huang, Honglin Jiang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/3899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850115679936577536
author Jing Yang
Shengqiang Zhou
Xialing Li
Yuchun Huang
Honglin Jiang
author_facet Jing Yang
Shengqiang Zhou
Xialing Li
Yuchun Huang
Honglin Jiang
author_sort Jing Yang
collection DOAJ
description Accurate extraction of table borders in scanned road engineering drawings is crucial for the digital transformation of engineering archives, which is an essential step in the development of intelligent infrastructure systems. However, challenges such as degraded borders, image blur, and character adjoining often hinder the precise delineation of table structures, making automated parsing difficult. Existing solutions, including traditional OCR tools and deep learning methods, struggle to consistently delineate table borders in the presence of these visual distortions and fail to perform well without extensive annotated datasets, which limits their effectiveness in real-world applications. We propose TableBorderNet, a semantic segmentation framework designed for precise border extraction under complex visual conditions. The framework captures structural context by guiding convolutional feature extraction along explicit row and column directions, enabling more accurate delineation of table borders. To ensure topological consistency in complex or degraded inputs, a topology-aware loss function is introduced, which explicitly penalizes structural discontinuities during training. Additionally, a generative self-supervised strategy simulates common degradation patterns, allowing the model to achieve strong performance with minimal reliance on manually annotated data. Experiments demonstrate that the method achieves an Intersection-over-Union of 94.2% and a topological error of 1.07%, outperforming existing approaches. These results underscore its practicality and scalability for accelerating the digitization of engineering drawings in support of data-driven road asset management.
format Article
id doaj-art-5ef09c605b2a44b9ab89fded52f7891a
institution OA Journals
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-5ef09c605b2a44b9ab89fded52f7891a2025-08-20T02:36:31ZengMDPI AGSensors1424-82202025-06-012513389910.3390/s25133899TableBorderNet: A Table Border Extraction Network Considering Topological RegularityJing Yang0Shengqiang Zhou1Xialing Li2Yuchun Huang3Honglin Jiang4School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaChina Railway Changjiang Transport Design Group Co., Ltd., Chongqing 401121, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaChina Railway Changjiang Transport Design Group Co., Ltd., Chongqing 401121, ChinaAccurate extraction of table borders in scanned road engineering drawings is crucial for the digital transformation of engineering archives, which is an essential step in the development of intelligent infrastructure systems. However, challenges such as degraded borders, image blur, and character adjoining often hinder the precise delineation of table structures, making automated parsing difficult. Existing solutions, including traditional OCR tools and deep learning methods, struggle to consistently delineate table borders in the presence of these visual distortions and fail to perform well without extensive annotated datasets, which limits their effectiveness in real-world applications. We propose TableBorderNet, a semantic segmentation framework designed for precise border extraction under complex visual conditions. The framework captures structural context by guiding convolutional feature extraction along explicit row and column directions, enabling more accurate delineation of table borders. To ensure topological consistency in complex or degraded inputs, a topology-aware loss function is introduced, which explicitly penalizes structural discontinuities during training. Additionally, a generative self-supervised strategy simulates common degradation patterns, allowing the model to achieve strong performance with minimal reliance on manually annotated data. Experiments demonstrate that the method achieves an Intersection-over-Union of 94.2% and a topological error of 1.07%, outperforming existing approaches. These results underscore its practicality and scalability for accelerating the digitization of engineering drawings in support of data-driven road asset management.https://www.mdpi.com/1424-8220/25/13/3899table border extractiondeep learningsemantic segmentationtopology-aware learning
spellingShingle Jing Yang
Shengqiang Zhou
Xialing Li
Yuchun Huang
Honglin Jiang
TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
Sensors
table border extraction
deep learning
semantic segmentation
topology-aware learning
title TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
title_full TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
title_fullStr TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
title_full_unstemmed TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
title_short TableBorderNet: A Table Border Extraction Network Considering Topological Regularity
title_sort tablebordernet a table border extraction network considering topological regularity
topic table border extraction
deep learning
semantic segmentation
topology-aware learning
url https://www.mdpi.com/1424-8220/25/13/3899
work_keys_str_mv AT jingyang tablebordernetatableborderextractionnetworkconsideringtopologicalregularity
AT shengqiangzhou tablebordernetatableborderextractionnetworkconsideringtopologicalregularity
AT xialingli tablebordernetatableborderextractionnetworkconsideringtopologicalregularity
AT yuchunhuang tablebordernetatableborderextractionnetworkconsideringtopologicalregularity
AT honglinjiang tablebordernetatableborderextractionnetworkconsideringtopologicalregularity