A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks
Condition monitoring and inspection are core activities for assessing and evaluating the health of critical infrastructure spanning from road networks to nuclear power stations. Defect detection on visual inspections of such assets is a field that enjoys increasing attention. However, data-based mod...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10058512/ |
_version_ | 1811155636509999104 |
---|---|
author | Efstathios Branikas Paul Murray Graeme West |
author_facet | Efstathios Branikas Paul Murray Graeme West |
author_sort | Efstathios Branikas |
collection | DOAJ |
description | Condition monitoring and inspection are core activities for assessing and evaluating the health of critical infrastructure spanning from road networks to nuclear power stations. Defect detection on visual inspections of such assets is a field that enjoys increasing attention. However, data-based models are prone to a lack of available data depicting cracks of various modalities and present a great data imbalance. This paper introduces a novel data augmentation technique by deploying the CycleGan Generative Adversarial Network (GAN). The proposed model is deployed between different image datasets depicting cracks, with a nuclear application as the main industrial example. The aim of this network is to improve the segmentation accuracy on these datasets using deep convolutional neural networks. The proposed GAN generates realistic images that are challenging to segment and under-represented in the original datasets. Different deep networks are trained with the augmented datasets while introducing no labelling overhead. A comparison is drawn between the performance of the different neural networks on the original data and their augmented counterparts. Extensive experiments suggest that the proposed augmentation method results in superior crack detection in challenging cases across all datasets. This is reflected by the respective increase in the quantitative evaluation metrics. |
first_indexed | 2024-04-10T04:36:47Z |
format | Article |
id | doaj.art-bc7bb8d64a544914b6111eafd0453b2e |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-10T04:36:47Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-bc7bb8d64a544914b6111eafd0453b2e2023-03-10T00:00:18ZengIEEEIEEE Access2169-35362023-01-0111220512205910.1109/ACCESS.2023.325198810058512A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial NetworksEfstathios Branikas0https://orcid.org/0000-0001-6045-6710Paul Murray1https://orcid.org/0000-0002-6980-9276Graeme West2https://orcid.org/0000-0003-0884-6070Department of Electronics and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Department of Electronics and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Department of Electronics and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Condition monitoring and inspection are core activities for assessing and evaluating the health of critical infrastructure spanning from road networks to nuclear power stations. Defect detection on visual inspections of such assets is a field that enjoys increasing attention. However, data-based models are prone to a lack of available data depicting cracks of various modalities and present a great data imbalance. This paper introduces a novel data augmentation technique by deploying the CycleGan Generative Adversarial Network (GAN). The proposed model is deployed between different image datasets depicting cracks, with a nuclear application as the main industrial example. The aim of this network is to improve the segmentation accuracy on these datasets using deep convolutional neural networks. The proposed GAN generates realistic images that are challenging to segment and under-represented in the original datasets. Different deep networks are trained with the augmented datasets while introducing no labelling overhead. A comparison is drawn between the performance of the different neural networks on the original data and their augmented counterparts. Extensive experiments suggest that the proposed augmentation method results in superior crack detection in challenging cases across all datasets. This is reflected by the respective increase in the quantitative evaluation metrics.https://ieeexplore.ieee.org/document/10058512/Crack segmentationgenerative adversarial networks (GANs)nuclear inspectionsdata augmentationimage-to-image translation |
spellingShingle | Efstathios Branikas Paul Murray Graeme West A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks IEEE Access Crack segmentation generative adversarial networks (GANs) nuclear inspections data augmentation image-to-image translation |
title | A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks |
title_full | A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks |
title_fullStr | A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks |
title_full_unstemmed | A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks |
title_short | A Novel Data Augmentation Method for Improved Visual Crack Detection Using Generative Adversarial Networks |
title_sort | novel data augmentation method for improved visual crack detection using generative adversarial networks |
topic | Crack segmentation generative adversarial networks (GANs) nuclear inspections data augmentation image-to-image translation |
url | https://ieeexplore.ieee.org/document/10058512/ |
work_keys_str_mv | AT efstathiosbranikas anoveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks AT paulmurray anoveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks AT graemewest anoveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks AT efstathiosbranikas noveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks AT paulmurray noveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks AT graemewest noveldataaugmentationmethodforimprovedvisualcrackdetectionusinggenerativeadversarialnetworks |