[en] 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 havebeen proposed, principal component thermography (PCT)—based on principal component analysis (PCA)—is 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)—based on RPCA, was evaluated with respect to PCT—based 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.
Research center :
STAR - Space sciences, Technologies and Astrophysics Research - ULiège
Disciplines :
Physics
Author, co-author :
Ebrahimi, Samira; Université Laval > Department of Electrical and Computer Engineering > Computer Vision and Systems laboratory
Fleuret, Julien; Université Laval > Department of Electrical and Computer Engineering > Computer Vision and Systems laboratory
Klein, Matthieu; Visiooimage
Théroux, Louis-Daniel; Centre Technologique en Aérospatial (CTA)
Georges, Marc ; Université de Liège - ULiège > CSL (Centre Spatial de Liège)
Ibarra-Castanedo, Clemente; Université Laval > Department of Electrical and Computer Engineering > Computer Vision and Systems laboratory
Maldague, Xavier; Université Laval > Department of Electrical and Computer Engineering > Computer Vision and Systems laboratory
Language :
English
Title :
Robust Principal Component Thermography for Defect Detection in Composites
Publication date :
10 April 2021
Journal title :
Sensors
ISSN :
1424-8220
eISSN :
1424-3210
Publisher :
Multidisciplinary Digital Publishing Institute (MDPI), Switzerland
Volume :
21
Pages :
2682
Peer reviewed :
Peer Reviewed verified by ORBi
Name of the research project :
LDCOMP
Funders :
Service public de Wallonie. Secrétariat général - SPW-SG
Vavilov, V.; Maldague, X. Optimization of heating protocol in thermal NDT, short and long heating pulses: A discussion. Res. Nondestruct. Eval. 1994, 6, 1–18.
Hotelling, H. Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 1933, 24, 417.
Pearson, K. LIII. On lines and planes of closest fit to systems of points in space. Lond. Edinb. Dublin Philos. Mag. J. Sci. 1901, 2, 559–572.
Rajic, N. Principal component thermography for flaw contrast enhancement and flaw depth characterisation in composite structures. Compos. Struct. 2002, 58, 521–528. doi:10.1016/S0263-8223(02)00161-7.
Candès, E.J.; Li, X.; Ma, Y.; Wright, J. Robust Principal Component Analysis? J. ACM 2011, 58. doi:10.1145/1970392.1970395.
Ebadi, S.E.; Izquierdo, E. Foreground segmentation with tree-structured sparse RPCA. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 2273–2280.
Bouwmans, T.; Zahzah, E.H. Robust PCA via principal component pursuit: A review for a comparative evaluation in video surveillance. Comput. Vis. Image Underst. 2014, 122, 22–34.
Luan, X.; Fang, B.; Liu, L.; Yang, W.; Qian, J. Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion. Pattern Recognit. 2014, 47, 495–508.
Gavrilescu, M. Noise robust automatic speech recognition system by integrating robust principal component analysis (RPCA) and exemplar-based sparse representation. In Proceedings of the 2015 7th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Bucharest, Romania, 25–27 June 2015; pp. S-29–S-34.
Deerwester, S.; Dumais, S.T.; Furnas, G.W.; Landauer, T.K.; Harshman, R. Indexing by latent semantic analysis. J. Am. Soc. Inf. Sci. 1990, 41, 391–407.
Song, Q.; Yan, G.; Tang, G.; Ansari, F. Robust principal component analysis and support vector machine for detection of microcracks with distributed optical fiber sensors. Mech. Syst. Signal Process. 2021, 146, 107019. doi:10.1016/j.ymssp.2020.107019.
Yao, J.; Liu, X.; Qi, C. Foreground detection using low rank and structured sparsity. In Proceedings of the 2014 IEEE International Conference on Multimedia and Expo (ICME), Chengdu, China, 14–18 July 2014; pp. 1–6.
Liu, X.; Zhao, G.; Yao, J.; Qi, C. Background subtraction based on low-rank and structured sparse decomposition. IEEE Trans. Image Process. 2015, 24, 2502–2514.
Guyon, C.; Bouwmans, T.; Zahzah, E.H. Foreground detection based on low-rank and block-sparse matrix decomposition. In Proceedings of the 2012 19th IEEE International Conference on Image Processing, Orlando, FL, USA, 30 September–3 October 2012; pp. 1225–1228.
Xue, Z.; Dong, J.; Zhao, Y.; Liu, C.; Chellali, R. Low-rank and sparse matrix decomposition via the truncated nuclear norm and a sparse regularizer. Vis. Comput. 2019, 35, 1549–1566.
Yang, B.; Zou, L. Robust foreground detection using block-based RPCA. Optik 2015, 126, 4586–4590.
Khan, M.A.; Kim, J. Toward Developing Efficient Conv-AE-Based Intrusion Detection System Using Heterogeneous Dataset. Electronics 2020, 9, 1771. doi:10.3390/electronics9111771.
Zhang, S.; Zhang, Q.; Gu, J.; Su, L.; Li, K.; Pecht, M. Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural network. Mech. Syst. Signal Process. 2021, 153, 107541. doi:10.1016/j.ymssp.2020.107541.
Fleuret, J.; Ibarra-Castanedo, C.; Lei, L.; Sfarra, S.; Usamentiaga, R.; Maldague, X. Defect detection based on monogenic signal processing. In Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV; International Society for Optics and Photonics: Bellingham, WA, USA, 2019; Volume 10986, p. 109861X.
Yousefi, B.; Sfarra, S.; Sarasini, F.; Castanedo, C.I.; Maldague, X.P. Low-rank sparse principal component thermography (sparse-PCT): Comparative assessment on detection of subsurface defects. Infrared Phys. Technol. 2019, 98, 278–284.
Wen, C.M.; Sfarra, S.; Gargiulo, G.; Yao, Y. Edge-Group Sparse Principal Component Thermography for Defect Detection in an Ancient Marquetry Sample. Proceedings 2019, 27, 34. doi:10.3390/proceedings2019027034.
Wen, C.M.; Sfarra, S.; Gargiulo, G.; Yao, Y. Thermographic Data Analysis for Defect Detection by Imposing Spatial Connectivity and Sparsity Constraints in Principal Component Thermography. IEEE Trans. Ind. Inform. 2021, 17, 3901–3909.
Min, W.; Liu, J.; Zhang, S. Edge-group sparse PCA for network-guided high dimensional data analysis. Bioinformatics 2018, 34, 3479–3487.
Yousefi, B.; Castanedo, C.I.; Maldague, X.P.V. Measuring Heterogeneous Thermal Patterns in Infrared-Based Diagnostic Systems Using Sparse Low-Rank Matrix Approximation: Comparative Study. IEEE Trans. Instrum. Meas. 2021, 70, 1–9. doi:10.1109/tim.2020.3031129.
Rengifo, C.J.; Restrepo, A.D.; Nope, S.E. Method of selecting independent components for defect detection in carbon fiberreinforced polymer sheets via pulsed thermography. Appl. Opt. 2018, 57, 9746–9754.
Liu, Y.; Wu, J.Y.; Liu, K.; Wen, H.L.; Yao, Y.; Sfarra, S.; Zhao, C. Independent component thermography for non-destructive testing of defects in polymer composites. Meas. Sci. Technol. 2019, 30, 044006.
Fleuret, J.; Ibarra-Castanedo, C.; Ebrahimi, S.; Maldague, X. Independent Component Thermography Applied to Pulsed Thermographic Data. In Proceedings of the 3rd International Symposium on Structural Health Monitoring and Nondestructive Testing, Québec City, QC, Canada, 14–15 May 2020.
Fleuret, J.; Ibarra-Castanedo, C.; Ebrahimi, S.; Maldague, X. Latent Low Rank Representation Applied to Thermography. In Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography, Porto, Portugal, 21–30 September 2020. doi:10.21611/qirt.2020.149.
Maldague, X.; Marinetti, S. Pulse phase infrared thermography. J. Appl. Phys. 1996, 79, 2694–2698.
Liu, K.; Li, Y.; Yang, J.; Liu, Y.; Yao, Y. Generative principal component thermography for enhanced defect detection and analysis. IEEE Trans. Instrum. Meas. 2020, 69, 8261–8269.
Rajic, N. Principal Component Thermography; Technical Report; Defence Science And Technology Organisation: Victoria, Australia, 2002.
Liu, K.; Tang, Y.; Lou, W.; Liu, Y.; Yang, J.; Yao, Y. A thermographic data augmentation and signal separation method for defect detection. Meas. Sci. Technol. 2021, 32, 045401.
Lopez, F.; Nicolau, V.; Maldague, X.; Ibarra-Castanedo, C. Multivariate infrared signal processing by partial least-squares thermography. In Proceedings of the 16th International Symposium on Applied Electromagnetics and Mechanics, Québec, QC, Canada, 31 July–3 August 2013.
Lopez, F.; Ibarra-Castanedo, C.; de Paulo Nicolau, V.; Maldague, X. Optimization of pulsed thermography inspection by partial least-squares regression. Ndt E Int. 2014, 66, 128–138.
Shepard, S.M.; Lhota, J.R.; Rubadeux, B.A.; Ahmed, T.; Wang, D. Enhancement and reconstruction of thermographic NDT data. In Thermosense XXIV; Maldague, X.P., Rozlosnik, A.E., Eds.; International Society for Optics and Photonics, SPIE: Bellingham, WA, USA, 2002; Volume 4710, pp. 531–535. doi:10.1117/12.459603.
Fleuret, J.; Ebrahimi, S.; Maldague, X. Pulsed Thermography Signal Reconstruction Using Linear Support Vector Regression. In Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography, Porto, Portugal, 21–30 September 2020. doi:10.21611/qirt.2020.150.
Vapnik, V.N. The Nature of Statistical Learning Theory; Springer: New York, NY, USA, 1995.
Zhu, P.; Cheng, Y.; Bai, L.; Tian, L. Local sparseness and image fusion for defect inspection in eddy current pulsed thermography. IEEE Sens. J. 2018, 19, 1471–1477.
Zhu, P.P.; Cheng, Y.H.; Bai, L.B. A Novel Feature Extraction Approach for Defect Inspection in Eddy Current Pulsed Thermography. J. Electron. Sci. Technol. 2020, 18, 1–10. doi:10.11989/JEST.1674-862X.90222016.
Liang, Y.; Bai, L.; Shao, J.; Cheng, Y. Application of Tensor Decomposition Methods In Eddy Current Pulsed Thermography Sequences Processing. In Proceedings of the 2020 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence (ICSMD), Xi’an, China, 15–17 October 2020; pp. 401–406.
Lu, C.; Feng, J.; Chen, Y.; Liu, W.; Lin, Z.; Yan, S. Tensor robust principal component analysis with a new tensor nuclear norm. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 42, 925–938.
Xiao, X.; Gao, B.; Woo, W.L.; Tian, G.Y.; Xiao, X.T. Spatial-time-state fusion algorithm for defect detection through eddy current pulsed thermography. Infrared Phys. Technol. 2018, 90, 133–145.
Peng, C.; Chen, Y.; Kang, Z.; Chen, C.; Cheng, Q. Robust principal component analysis: A factorization-based approach with linear complexity. Inf. Sci. 2020, 513, 581–599.
Sun, W.; Du, Q. Graph-regularized fast and robust principal component analysis for hyperspectral band selection. IEEE Trans. Geosci. Remote Sens. 2018, 56, 3185–3195.
Liu, Y.; Gao, X.; Gao, Q.; Shao, L.; Han, J. Adaptive robust principal component analysis. Neural Netw. 2019, 119, 85–92.
Wang, Q.; Gao, Q.; Sun, G.; Ding, C. Double robust principal component analysis. Neurocomputing 2020, 391, 119–128.
Ma, S.; Aybat, N.S. Efficient optimization algorithms for robust principal component analysis and its variants. Proc. IEEE 2018, 106, 1411–1426.
Van Luong, H.; Deligiannis, N.; Seiler, J.; Forchhammer, S.; Kaup, A. Compressive Online Robust Principal Component Analysis via n-ℓ1 Minimization. IEEE Trans. Image Process. 2018, 27, 4314–4329. doi:10.1109/TIP.2018.2831915.
Cai, H.; Hamm, K.; Huang, L.; Li, J.; Wang, T. Rapid Robust Principal Component Analysis: CUR Accelerated Inexact Low Rank Estimation. IEEE Signal Process. Lett. 2021, 28, 116–120.
Lin, Z.; Chen, M.; Ma, Y. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv 2010, arXiv:1009.5055.
Candès, E.J.; Recht, B. Exact matrix completion via convex optimization. Found. Comput. Math. 2009, 9, 717–772.
Blain, P.; Vandenrijt, J.F.; Languy, F.; Kirkove, M.; Théroux, L.D.; Lewandowski, J.; Georges, M. Artificial defects in CFRP composite structure for thermography and shearography nondestructive inspection. In Proceedings of the Fifth International Conference on Optical and Photonics Engineering, Singapore, 4–7 April 2017; International Society for Optics and Photonics: Bellingham, WA, USA, 2017; Volume. 10449, p. 104493H.
Vandenrijt, J.F.; Lièvre, N.; Georges, M.P. Improvement of defect detection in shearography by using principal component analysis. In Interferometry XVII: Techniques and Analysis; International Society for Optics and Photonics: Bellingham, WA, USA, 2014; Volume 9203, p. 92030L.
Kirkove, M.; Zhao, Y.; Blain, P.; Vandenrijt, J.F.; Georges, M. Thermography-inspired processing strategy applied on shearography towards nondestructive inspection of composites. In Optical Measurement Systems for Industrial Inspection XI; International Society for Optics and Photonics: Bellingham, WA, USA, 2019; Volume 11056, p. 110560G.
Usamentiaga, R.; Ibarra-Castanedo, C.; Maldague, X. More than fifty shades of grey: Quantitative characterization of defects and interpretation using SNR and CNR. J. Nondestruct. Eval. 2018, 37, 1–17. doi:10.1007/s10921-018-0479-z.
Jaccard, P. Lois de distribution florale dans la zone alpine. Bull. Société Vaudoise Sci. Nat. 1902, 38, 69–130. doi:10.5169/seals 266762.
Tomasi, C.; Manduchi, R. Bilateral filtering for gray and color images. In Proceedings of the Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271), Bombay, India, 7 January 1998; pp. 839–846.
