Spatial and temporal deep learning algorithms for defect segmentation in infrared thermographic imaging of carbon fibre-reinforced polymers

Simple item page
dc.contributor.authorGarcia Vargas, Iago
dc.contributor.authorFernandes, Henrique
dc.date.accessioned2025-03-03T11:43:14Z
dc.date.available2025-03-03T11:43:14Z
dc.date.freetoread2025-03-03
dc.date.issued2025-01-24
dc.date.pubOnline2025-01-24
dc.description.abstractFor non-destructive evaluation, the segmentation of infrared thermographic images of carbon fibre composites is a critical task in material characterisation and quality assessment. This paper presents a study on the application of image processing techniques, particularly adaptive thresholding, and advanced neural network models, including U-Net, DeepLabv3, and BiLSTM, for the segmentation of infrared images. This work introduces the innovative combination of DeepLabv3 and BiLSTM applied in infrared images of carbon fibre-reinforced polymer samples for the first time, proposing it as a novel approach for enhancing the accuracy of segmentation tasks. An experimental comparison of these models was conducted to assess their effectiveness in identifying artificial defects in these images. The performance of each model was evaluated using the F1-Score and Intersection over Union (IoU) metrics. The results demonstrate that the proposed combination of DeepLabv3 and BiLSTM outperforms other methods, achieving an F1-Score of 0.96 and an IoU of 0.83, showcasing its potential for advanced material analysis and quality control.
dc.description.journalNameNondestructive Testing and Evaluation
dc.description.sponsorshipNational Council for Scientific and Technological Development, Coordenação de Aperfeicoamento de Pessoal de Nível Superior
dc.description.sponsorshipThis study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code [001] and by the National Council for Scientific and Technological Development - Brazil (CNPq) – Finance Codes [407140/2021–2] and [312530/2023–4].
dc.format.extentpp. xx-xx
dc.identifier.citationGarcia Vargas I, Fernandes H. (2025) Spatial and temporal deep learning algorithms for defect segmentation in infrared thermographic imaging of carbon fibre-reinforced polymers. Nondestructive Testing and Evaluation, Available online 24 January 2025
dc.identifier.eissn1477-2671
dc.identifier.elementsID563492
dc.identifier.issn1058-9759
dc.identifier.issueNoahead-of-print
dc.identifier.urihttps://doi.org/10.1080/10589759.2025.2457593
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23532
dc.identifier.volumeNoahead-of-print
dc.languageEnglish
dc.language.isoen
dc.publisherTaylor and Francis
dc.publisher.urihttps://www.tandfonline.com/doi/full/10.1080/10589759.2025.2457593
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectInfrared thermograph
dc.subjectsegmentation
dc.subjectU-Net
dc.subjectDeepLabv3
dc.subjectBiLSTM
dc.subjectcomposite material
dc.subject40 Engineering
dc.subject4016 Materials Engineering
dc.subjectMachine Learning and Artificial Intelligence
dc.subjectAcoustics
dc.subject4016 Materials engineering
dc.titleSpatial and temporal deep learning algorithms for defect segmentation in infrared thermographic imaging of carbon fibre-reinforced polymers
dc.typeArticle
dc.type.subtypeJournal Article
dcterms.dateAccepted2025-01-17

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Spatial_and_temporal_deep_learning_algorithms-2025.pdf
Size:
3.56 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Plain Text
Description:
Download

Collections

Staff publications (SATM)