A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion

In response to the limitations of traditional image processing algorithms, such as high noise sensitivity and threshold dependency in bridge crack detection, and the extensive labeled data requirements of deep learning methods, this study proposes a novel crack segmentation algorithm based on fuzzy...

Full description

Saved in:
Bibliographic Details
Main Authors: Yadong Yao, Yurui Zhang, Zai Liu, Heming Yuan
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/14/4399
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850072417261584384
author Yadong Yao
Yurui Zhang
Zai Liu
Heming Yuan
author_facet Yadong Yao
Yurui Zhang
Zai Liu
Heming Yuan
author_sort Yadong Yao
collection DOAJ
description In response to the limitations of traditional image processing algorithms, such as high noise sensitivity and threshold dependency in bridge crack detection, and the extensive labeled data requirements of deep learning methods, this study proposes a novel crack segmentation algorithm based on fuzzy C-means (FCM) clustering and multi-feature fusion. A three-dimensional feature space is constructed using B-channel pixels and fuzzy clustering with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>c</mi></semantics></math></inline-formula> = 3, justified by the distinct distribution patterns of these three regions in the image, enabling effective preliminary segmentation. To enhance accuracy, connected domain labeling combined with a circularity threshold is introduced to differentiate linear cracks from granular noise. Furthermore, a 5 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mo>×</mo></semantics></math></inline-formula> 5 neighborhood search strategy, based on crack pixel amplitude, is designed to restore the continuity of fragmented cracks. Experimental results on the Concrete Crack and SDNET2018 datasets demonstrate that the proposed algorithm achieves an accuracy of 0.885 and a recall rate of 0.891, outperforming DeepLabv3+ by 4.2%. Notably, with a processing time of only 0.8 s per image, the algorithm balances high accuracy with real-time efficiency, effectively addressing challenges, such as missed fine cracks and misjudged broken cracks in noisy environments by integrating geometric features and pixel distribution characteristics. This study provides an efficient unsupervised solution for bridge damage detection.
format Article
id doaj-art-8c1bc4dfd943457e9fd1672e394678b3
institution DOAJ
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-8c1bc4dfd943457e9fd1672e394678b32025-08-20T02:47:05ZengMDPI AGSensors1424-82202025-07-012514439910.3390/s25144399A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature FusionYadong Yao0Yurui Zhang1Zai Liu2Heming Yuan3Institute of Transportation, Inner Mongolia University, Hohhot 010070, ChinaInstitute of Transportation, Inner Mongolia University, Hohhot 010070, ChinaInstitute of Transportation, Inner Mongolia University, Hohhot 010070, ChinaInstitute of Transportation, Inner Mongolia University, Hohhot 010070, ChinaIn response to the limitations of traditional image processing algorithms, such as high noise sensitivity and threshold dependency in bridge crack detection, and the extensive labeled data requirements of deep learning methods, this study proposes a novel crack segmentation algorithm based on fuzzy C-means (FCM) clustering and multi-feature fusion. A three-dimensional feature space is constructed using B-channel pixels and fuzzy clustering with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>c</mi></semantics></math></inline-formula> = 3, justified by the distinct distribution patterns of these three regions in the image, enabling effective preliminary segmentation. To enhance accuracy, connected domain labeling combined with a circularity threshold is introduced to differentiate linear cracks from granular noise. Furthermore, a 5 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mo>×</mo></semantics></math></inline-formula> 5 neighborhood search strategy, based on crack pixel amplitude, is designed to restore the continuity of fragmented cracks. Experimental results on the Concrete Crack and SDNET2018 datasets demonstrate that the proposed algorithm achieves an accuracy of 0.885 and a recall rate of 0.891, outperforming DeepLabv3+ by 4.2%. Notably, with a processing time of only 0.8 s per image, the algorithm balances high accuracy with real-time efficiency, effectively addressing challenges, such as missed fine cracks and misjudged broken cracks in noisy environments by integrating geometric features and pixel distribution characteristics. This study provides an efficient unsupervised solution for bridge damage detection.https://www.mdpi.com/1424-8220/25/14/4399fuzzy C-means clusteringbridge crack detectionmulti-feature fusionconnected domain labelingcircularity thresholdunsupervised detection
spellingShingle Yadong Yao
Yurui Zhang
Zai Liu
Heming Yuan
A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
Sensors
fuzzy C-means clustering
bridge crack detection
multi-feature fusion
connected domain labeling
circularity threshold
unsupervised detection
title A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
title_full A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
title_fullStr A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
title_full_unstemmed A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
title_short A Bridge Crack Segmentation Algorithm Based on Fuzzy C-Means Clustering and Feature Fusion
title_sort bridge crack segmentation algorithm based on fuzzy c means clustering and feature fusion
topic fuzzy C-means clustering
bridge crack detection
multi-feature fusion
connected domain labeling
circularity threshold
unsupervised detection
url https://www.mdpi.com/1424-8220/25/14/4399
work_keys_str_mv AT yadongyao abridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT yuruizhang abridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT zailiu abridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT hemingyuan abridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT yadongyao bridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT yuruizhang bridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT zailiu bridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion
AT hemingyuan bridgecracksegmentationalgorithmbasedonfuzzycmeansclusteringandfeaturefusion