{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T07:52:22Z","timestamp":1774425142661,"version":"3.50.1"},"reference-count":60,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T00:00:00Z","timestamp":1618012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Minist\u00e8re de l\u2019\u00c9conomie et de l\u2019Innovation- Qu\u00e9bec (MEI)","award":["2018-Pl-1-SQA"],"award-info":[{"award-number":["2018-Pl-1-SQA"]}]},{"name":"SKYWIN (Wallonie, Belgium, Convention n\u00b0 8188)","award":["project 11.812"],"award-info":[{"award-number":["project 11.812"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Pulsed Thermography (PT) data are usually affected by noise and as such most of the research effort in the last few years has been directed towards the development of advanced signal processing methods to improve defect detection. Among the numerous techniques that have been proposed, principal component thermography (PCT)\u2014based on principal component analysis (PCA)\u2014is one of the most effective in terms of defect contrast enhancement and data compression. However, it is well-known that PCA can be significantly affected in the presence of corrupted data (e.g., noise and outliers). Robust PCA (RPCA) has been recently proposed as an alternative statistical method that handles noisy data more properly by decomposing the input data into a low-rank matrix and a sparse matrix. We propose to process PT data by RPCA instead of PCA in order to improve defect detectability. The performance of the resulting approach, Robust Principal Component Thermography (RPCT)\u2014based on RPCA, was evaluated with respect to PCT\u2014based on PCA, using a CFRP sample containing artificially produced defects. We compared results quantitatively based on two metrics, Contrast-to-Noise Ratio (CNR), for defect detection capabilities, and the Jaccard similarity coefficient, for defect segmentation potential. CNR results were on average 40% higher for RPCT than for PCT, and the Jaccard index was slightly higher for RPCT (0.7395) than for PCT (0.7010). In terms of computational time, however, PCT was 11.5 times faster than RPCT. Further investigations are needed to assess RPCT performance on a wider range of materials and to optimize computational time.<\/jats:p>","DOI":"10.3390\/s21082682","type":"journal-article","created":{"date-parts":[[2021,4,12]],"date-time":"2021-04-12T05:52:00Z","timestamp":1618206720000},"page":"2682","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Robust Principal Component Thermography for Defect Detection in Composites"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6769-1705","authenticated-orcid":false,"given":"Samira","family":"Ebrahimi","sequence":"first","affiliation":[{"name":"Computer Vision and Systems Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC G1V 0A6, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5017-2378","authenticated-orcid":false,"given":"Julien","family":"Fleuret","sequence":"additional","affiliation":[{"name":"Computer Vision and Systems Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC G1V 0A6, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7811-388X","authenticated-orcid":false,"given":"Matthieu","family":"Klein","sequence":"additional","affiliation":[{"name":"Infrared Thermography Testing Systems, Visiooimage Inc., Quebec City, QC G1W 1A8, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5388-8355","authenticated-orcid":false,"given":"Louis-Daniel","family":"Th\u00e9roux","sequence":"additional","affiliation":[{"name":"Centre Technologique et A\u00e9rospatial (CTA), Saint-Hubert, QC J3Y 8Y9, Canada"}]},{"given":"Marc","family":"Georges","sequence":"additional","affiliation":[{"name":"Centre Spatial de Li\u00e8ge, STAR Research Unit, Li\u00e8ge Universit\u00e9, 4031 Angleur, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0198-7439","authenticated-orcid":false,"given":"Clemente","family":"Ibarra-Castanedo","sequence":"additional","affiliation":[{"name":"Computer Vision and Systems Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC G1V 0A6, Canada"},{"name":"Infrared Thermography Testing Systems, Visiooimage Inc., Quebec City, QC G1W 1A8, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8777-2008","authenticated-orcid":false,"given":"Xavier","family":"Maldague","sequence":"additional","affiliation":[{"name":"Computer Vision and Systems Laboratory (CVSL), Department of Electrical and Computer Engineering, Laval University, Quebec City, QC G1V 0A6, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/09349849409409677","article-title":"Optimization of heating protocol in thermal NDT, short and long heating pulses: A discussion","volume":"6","author":"Vavilov","year":"1994","journal-title":"Res. Nondestruct. Eval."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1037\/h0071325","article-title":"Analysis of a complex of statistical variables into principal components","volume":"24","author":"Hotelling","year":"1933","journal-title":"J. Educ. Psychol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"Pearson","year":"1901","journal-title":"Lond. Edinb. Dublin Philos. Mag. J. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0263-8223(02)00161-7","article-title":"Principal component thermography for flaw contrast enhancement and flaw depth characterisation in composite structures","volume":"58","author":"Rajic","year":"2002","journal-title":"Compos. Struct."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Cand\u00e8s, E.J., Li, X., Ma, Y., and Wright, J. (2011). Robust Principal Component Analysis?. J. ACM, 58.","DOI":"10.1145\/1970392.1970395"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2273","DOI":"10.1109\/TPAMI.2017.2745573","article-title":"Foreground segmentation with tree-structured sparse RPCA","volume":"40","author":"Ebadi","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.cviu.2013.11.009","article-title":"Robust PCA via principal component pursuit: A review for a comparative evaluation in video surveillance","volume":"122","author":"Bouwmans","year":"2014","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/j.patcog.2013.06.031","article-title":"Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion","volume":"47","author":"Luan","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gavrilescu, M. (2015, January 25\u201327). Noise robust automatic speech recognition system by integrating robust principal component analysis (RPCA) and exemplar-based sparse representation. Proceedings of the 2015 7th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Bucharest, Romania.","DOI":"10.1109\/ECAI.2015.7301157"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","article-title":"Indexing by latent semantic analysis","volume":"41","author":"Deerwester","year":"1990","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"107019","DOI":"10.1016\/j.ymssp.2020.107019","article-title":"Robust principal component analysis and support vector machine for detection of microcracks with distributed optical fiber sensors","volume":"146","author":"Song","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yao, J., Liu, X., and Qi, C. (2014, January 14\u201318). Foreground detection using low rank and structured sparsity. Proceedings of the 2014 IEEE International Conference on Multimedia and Expo (ICME), Chengdu, China.","DOI":"10.1109\/ICME.2014.6890200"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1109\/TIP.2015.2419084","article-title":"Background subtraction based on low-rank and structured sparse decomposition","volume":"24","author":"Liu","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Guyon, C., Bouwmans, T., and Zahzah, E.H. (October, January 30). Foreground detection based on low-rank and block-sparse matrix decomposition. Proceedings of the 2012 19th IEEE International Conference on Image Processing, Orlando, FL, USA.","DOI":"10.1109\/ICIP.2012.6467087"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1007\/s00371-018-1555-1","article-title":"Low-rank and sparse matrix decomposition via the truncated nuclear norm and a sparse regularizer","volume":"35","author":"Xue","year":"2019","journal-title":"Vis. Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4586","DOI":"10.1016\/j.ijleo.2015.08.064","article-title":"Robust foreground detection using block-based RPCA","volume":"126","author":"Yang","year":"2015","journal-title":"Optik"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Khan, M.A., and Kim, J. (2020). Toward Developing Efficient Conv-AE-Based Intrusion Detection System Using Heterogeneous Dataset. Electronics, 9.","DOI":"10.3390\/electronics9111771"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"107541","DOI":"10.1016\/j.ymssp.2020.107541","article-title":"Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network","volume":"153","author":"Zhang","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_19","first-page":"109861X","article-title":"Defect detection based on monogenic signal processing","volume":"Volume 10986","author":"Fleuret","year":"2019","journal-title":"Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.infrared.2019.03.012","article-title":"Low-rank sparse principal component thermography (sparse-PCT): Comparative assessment on detection of subsurface defects","volume":"98","author":"Yousefi","year":"2019","journal-title":"Infrared Phys. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wen, C.M., Sfarra, S., Gargiulo, G., and Yao, Y. (2019). Edge-Group Sparse Principal Component Thermography for Defect Detection in an Ancient Marquetry Sample. Proceedings, 27.","DOI":"10.3390\/proceedings2019027034"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3901","DOI":"10.1109\/TII.2020.3010273","article-title":"Thermographic Data Analysis for Defect Detection by Imposing Spatial Connectivity and Sparsity Constraints in Principal Component Thermography","volume":"17","author":"Wen","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3479","DOI":"10.1093\/bioinformatics\/bty362","article-title":"Edge-group sparse PCA for network-guided high dimensional data analysis","volume":"34","author":"Min","year":"2018","journal-title":"Bioinformatics"},{"key":"ref_24","unstructured":"Yousefi, B., Castanedo, C.I., and Maldague, X.P. (2020). Low-rank Convex\/Sparse Thermal Matrix Approximation for Infrared-based Diagnostic System. arXiv."},{"key":"ref_25","first-page":"1","article-title":"Measuring Heterogeneous Thermal Patterns in Infrared-Based Diagnostic Systems Using Sparse Low-Rank Matrix Approximation: Comparative Study","volume":"70","author":"Yousefi","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"9746","DOI":"10.1364\/AO.57.009746","article-title":"Method of selecting independent components for defect detection in carbon fiber-reinforced polymer sheets via pulsed thermography","volume":"57","author":"Rengifo","year":"2018","journal-title":"Appl. Opt."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"044006","DOI":"10.1088\/1361-6501\/ab02db","article-title":"Independent component thermography for non-destructive testing of defects in polymer composites","volume":"30","author":"Liu","year":"2019","journal-title":"Meas. Sci. Technol."},{"key":"ref_28","unstructured":"Fleuret, J., Ibarra-Castanedo, C., Ebrahimi, S., and Maldague, X. (2020, January 14\u201315). Independent Component Thermography Applied to Pulsed Thermographic Data. Proceedings of the 3rd International Symposium on Structural Health Monitoring and Nondestructive Testing, Qu\u00e9bec City, QC, Canada."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Fleuret, J., Ibarra-Castanedo, C., Ebrahimi, S., and Maldague, X. (2020, January 21\u201330). Latent Low Rank Representation Applied to Thermography. Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography, Porto, Portugal.","DOI":"10.21611\/qirt.2020.149"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2694","DOI":"10.1063\/1.362662","article-title":"Pulse phase infrared thermography","volume":"79","author":"Maldague","year":"1996","journal-title":"J. Appl. Phys."},{"key":"ref_31","first-page":"8261","article-title":"Generative principal component thermography for enhanced defect detection and analysis","volume":"69","author":"Liu","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_32","unstructured":"Rajic, N. (2002). Principal Component Thermography, Defence Science And Technology Organisation. Technical Report."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"045401","DOI":"10.1088\/1361-6501\/abc63f","article-title":"A thermographic data augmentation and signal separation method for defect detection","volume":"32","author":"Liu","year":"2021","journal-title":"Meas. Sci. Technol."},{"key":"ref_34","unstructured":"Lopez, F., Nicolau, V., Maldague, X., and Ibarra-Castanedo, C. (August, January 31). Multivariate infrared signal processing by partial least-squares thermography. Proceedings of the 16th International Symposium on Applied Electromagnetics and Mechanics, Qu\u00e9bec, QC, Canada."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.ndteint.2014.06.003","article-title":"Optimization of pulsed thermography inspection by partial least-squares regression","volume":"66","author":"Lopez","year":"2014","journal-title":"NDT E Int."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1117\/12.459603","article-title":"Enhancement and reconstruction of thermographic NDT data","volume":"Volume 4710","author":"Maldague","year":"2002","journal-title":"Thermosense XXIV"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Fleuret, J., Ebrahimi, S., and Maldague, X. (2020, January 21\u201330). Pulsed Thermography Signal Reconstruction Using Linear Support Vector Regression. Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography, Porto, Portugal.","DOI":"10.21611\/qirt.2020.150"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Vapnik, V.N. (1995). The Nature of Statistical Learning Theory, Springer.","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1109\/JSEN.2018.2882131","article-title":"Local sparseness and image fusion for defect inspection in eddy current pulsed thermography","volume":"19","author":"Zhu","year":"2018","journal-title":"IEEE Sens. J."},{"key":"ref_40","first-page":"1","article-title":"A Novel Feature Extraction Approach for Defect Inspection in Eddy Current Pulsed Thermography","volume":"18","author":"Zhu","year":"2020","journal-title":"J. Electron. Sci. Technol."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Liang, Y., Bai, L., Shao, J., and Cheng, Y. (2020, January 15\u201317). Application of Tensor Decomposition Methods In Eddy Current Pulsed Thermography Sequences Processing. Proceedings of the 2020 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence (ICSMD), Xi\u2019an, China.","DOI":"10.1109\/ICSMD50554.2020.9261720"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1109\/TPAMI.2019.2891760","article-title":"Tensor robust principal component analysis with a new tensor nuclear norm","volume":"42","author":"Lu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.infrared.2018.02.012","article-title":"Spatial-time-state fusion algorithm for defect detection through eddy current pulsed thermography","volume":"90","author":"Xiao","year":"2018","journal-title":"Infrared Phys. Technol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1016\/j.ins.2019.09.074","article-title":"Robust principal component analysis: A factorization-based approach with linear complexity","volume":"513","author":"Peng","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3185","DOI":"10.1109\/TGRS.2018.2794443","article-title":"Graph-regularized fast and robust principal component analysis for hyperspectral band selection","volume":"56","author":"Sun","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2019.07.015","article-title":"Adaptive robust principal component analysis","volume":"119","author":"Liu","year":"2019","journal-title":"Neural Netw."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neucom.2020.01.097","article-title":"Double robust principal component analysis","volume":"391","author":"Wang","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1109\/JPROC.2018.2846606","article-title":"Efficient optimization algorithms for robust principal component analysis and its variants","volume":"106","author":"Ma","year":"2018","journal-title":"Proc. IEEE"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"4314","DOI":"10.1109\/TIP.2018.2831915","article-title":"Compressive Online Robust Principal Component Analysis via n - \u21131 Minimization","volume":"27","author":"Deligiannis","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/LSP.2020.3044130","article-title":"Rapid Robust Principal Component Analysis: CUR Accelerated Inexact Low Rank Estimation","volume":"28","author":"Cai","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_51","unstructured":"Lin, Z., Chen, M., and Ma, Y. (2010). The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1007\/s10208-009-9045-5","article-title":"Exact matrix completion via convex optimization","volume":"9","author":"Recht","year":"2009","journal-title":"Found. Comput. Math."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s11263-007-0075-7","article-title":"Incremental learning for robust visual tracking","volume":"77","author":"Ross","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_54","unstructured":"Beaumont, P.W., Zweben, C.H., Gdutos, E., Talreja, R., Poursartip, A., Clyne, T.W., Ruggles-Wrenn, M.B., Peijs, T., Thostenson, E.T., and Crane, R. (2018). Comprehensive Composite Materials II, Elsevier."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"104493H","DOI":"10.1117\/12.2271701","article-title":"Artificial defects in CFRP composite structure for thermography and shearography nondestructive inspection","volume":"Volume 10449","author":"Blain","year":"2017","journal-title":"Proceedings of the Fifth International Conference on Optical and Photonics Engineering"},{"key":"ref_56","first-page":"92030L","article-title":"Improvement of defect detection in shearography by using principal component analysis","volume":"Volume 9203","author":"Vandenrijt","year":"2014","journal-title":"Interferometry XVII: Techniques and Analysis"},{"key":"ref_57","first-page":"110560G","article-title":"Thermography-inspired processing strategy applied on shearography towards nondestructive inspection of composites","volume":"Volume 11056","author":"Kirkove","year":"2019","journal-title":"Optical Measurement Systems for Industrial Inspection XI"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10921-018-0479-z","article-title":"More than fifty shades of grey: Quantitative characterization of defects and interpretation using SNR and CNR","volume":"37","author":"Usamentiaga","year":"2018","journal-title":"J. Nondestruct. Eval."},{"key":"ref_59","first-page":"69","article-title":"Lois de distribution florale dans la zone alpine","volume":"38","author":"Jaccard","year":"1902","journal-title":"Bull. Soci\u00e9t\u00e9 Vaudoise Sci. Nat."},{"key":"ref_60","unstructured":"Tomasi, C., and Manduchi, R. (1998, January 7). Bilateral filtering for gray and color images. Proceedings of the Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271), Bombay, India."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/8\/2682\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:59:23Z","timestamp":1760363963000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/8\/2682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,10]]},"references-count":60,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,4]]}},"alternative-id":["s21082682"],"URL":"https:\/\/doi.org\/10.3390\/s21082682","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,10]]}}}