Staff View: MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer

MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer

In the domain of road inspection and structural health monitoring, precise crack identification and segmentation are essential for structural safety and disaster prediction. Traditional image processing technologies encounter difficulties in detecting cracks due to their morphological diversity and...

Full description

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yang, Ali, Raza, Mokhtar, Norrima, Harun, Sulaiman Wadi, Iwahashi, Masahiro
Format:	Article
Published:	Institute of Electrical and Electronics Engineers 2024
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.um.edu.my/47134/ https://doi.org/10.1109/ACCESS.2024.3438112
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.47134
record_format	eprints
spelling	my.um.eprints.471342024-12-09T05:06:38Z http://eprints.um.edu.my/47134/ MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer Zhou, Yang Ali, Raza Mokhtar, Norrima Harun, Sulaiman Wadi Iwahashi, Masahiro TK Electrical engineering. Electronics Nuclear engineering In the domain of road inspection and structural health monitoring, precise crack identification and segmentation are essential for structural safety and disaster prediction. Traditional image processing technologies encounter difficulties in detecting cracks due to their morphological diversity and complex background noise. This results in low detection accuracy and poor generalization. To overcome these challenges, this paper introduces MixSegNet, a novel deep learning model that enhances crack recognition and segmentation by integrating multi-scale features and deep feature learning. MixSegNet integrates convolutional neural networks (CNNs) and transformer architectures to enhance the detection of small cracks through the extraction and fusion of fine-grained features. Comparative evaluations against mainstream models, including LRASPP, U-Net, Deeplabv3, Swin-UNet, AttuNet, and FCN, demonstrate that MixSegNet achieves superior performance on open-source datasets. Specifically, the model achieved a precision of 95.2%, a recall of 88.2%, an F1 score of 91.5%, and a mean intersection over union (mIoU) of 84.8%, thereby demonstrating its effectiveness and reliability for crack segmentation tasks. Institute of Electrical and Electronics Engineers 2024 Article PeerReviewed Zhou, Yang and Ali, Raza and Mokhtar, Norrima and Harun, Sulaiman Wadi and Iwahashi, Masahiro (2024) MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer. IEEE Access, 12. pp. 111535-111545. ISSN 2169-3536, DOI https://doi.org/10.1109/ACCESS.2024.3438112 <https://doi.org/10.1109/ACCESS.2024.3438112>. https://doi.org/10.1109/ACCESS.2024.3438112 10.1109/ACCESS.2024.3438112
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Zhou, Yang Ali, Raza Mokhtar, Norrima Harun, Sulaiman Wadi Iwahashi, Masahiro MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
description	In the domain of road inspection and structural health monitoring, precise crack identification and segmentation are essential for structural safety and disaster prediction. Traditional image processing technologies encounter difficulties in detecting cracks due to their morphological diversity and complex background noise. This results in low detection accuracy and poor generalization. To overcome these challenges, this paper introduces MixSegNet, a novel deep learning model that enhances crack recognition and segmentation by integrating multi-scale features and deep feature learning. MixSegNet integrates convolutional neural networks (CNNs) and transformer architectures to enhance the detection of small cracks through the extraction and fusion of fine-grained features. Comparative evaluations against mainstream models, including LRASPP, U-Net, Deeplabv3, Swin-UNet, AttuNet, and FCN, demonstrate that MixSegNet achieves superior performance on open-source datasets. Specifically, the model achieved a precision of 95.2%, a recall of 88.2%, an F1 score of 91.5%, and a mean intersection over union (mIoU) of 84.8%, thereby demonstrating its effectiveness and reliability for crack segmentation tasks.
format	Article
author	Zhou, Yang Ali, Raza Mokhtar, Norrima Harun, Sulaiman Wadi Iwahashi, Masahiro
author_facet	Zhou, Yang Ali, Raza Mokhtar, Norrima Harun, Sulaiman Wadi Iwahashi, Masahiro
author_sort	Zhou, Yang
title	MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
title_short	MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
title_full	MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
title_fullStr	MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
title_full_unstemmed	MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer
title_sort	mixsegnet: a novel crack segmentation network combining cnn and transformer
publisher	Institute of Electrical and Electronics Engineers
publishDate	2024
url	http://eprints.um.edu.my/47134/ https://doi.org/10.1109/ACCESS.2024.3438112
_version_	1818834238122754048
score	13.223943

MixSegNet: A Novel Crack Segmentation Network Combining CNN and Transformer

Similar Items