{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T23:32:34Z","timestamp":1773185554313,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022073"],"award-info":[{"award-number":["62022073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873241"],"award-info":[{"award-number":["61873241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSTC 111-2221-E-007-005"],"award-info":[{"award-number":["NSTC 111-2221-E-007-005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Council, ROC","award":["62022073"],"award-info":[{"award-number":["62022073"]}]},{"name":"National Science and Technology Council, ROC","award":["61873241"],"award-info":[{"award-number":["61873241"]}]},{"name":"National Science and Technology Council, ROC","award":["NSTC 111-2221-E-007-005"],"award-info":[{"award-number":["NSTC 111-2221-E-007-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Infrared thermography is a widely utilized nondestructive testing technique in the field of artwork inspection. However, raw thermograms often suffer from problems, such as limited quantity and high background noise, due to limitations inherent in the acquisition equipment and experimental environment. To overcome these challenges, there is a growing interest in developing thermographic data enhancement methods. In this study, a defect inspection method for artwork based on principal component analysis is proposed, incorporating two distinct deep learning approaches for thermographic data enhancement: spectral normalized generative adversarial network (SNGAN) and convolutional autoencoder (CAE). The SNGAN strategy focuses on augmenting the thermal images, while the CAE strategy emphasizes enhancing their quality. Subsequently, principal component thermography (PCT) is employed to analyze the processed data and improve the detectability of defects. Comparing the results to using PCT alone, the integration of the SNGAN strategy led to a 1.08% enhancement in the signal-to-noise ratio, while the utilization of the CAE strategy resulted in an 8.73% improvement.<\/jats:p>","DOI":"10.3390\/s23146362","type":"journal-article","created":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T00:49:30Z","timestamp":1689295770000},"page":"6362","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Generative Deep Learning-Based Thermographic Inspection of Artwork"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4066-689X","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Process Equipment and Control Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"given":"Fumin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Process Equipment and Control Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"given":"Zhili","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Process Equipment and Control Engineering, Zhejiang University of Technology, Hangzhou 310023, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9354-4650","authenticated-orcid":false,"given":"Stefano","family":"Sfarra","sequence":"additional","affiliation":[{"name":"Department of Industrial and Information Engineering and Economics, University of L\u2019Aquila, Piazzale E. Pontieri n. 1, Monteluco di Roio, I-67100 L\u2019Aquila, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-1781","authenticated-orcid":false,"given":"Kaixin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanxi Key Laboratory of Signal Capturing & Processing, North University of China, Taiyuan 030051, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0025-6175","authenticated-orcid":false,"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, National Tsing Hua University, Hsinchu 300044, Taiwan"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Garrido, I., Erazo-Aux, J., Lag\u00fcela, S., Sfarra, S., Ibarra-Castanedo, C., Pivar\u010diov\u00e1, E., Gargiulo, G., Maldague, X., and Arias, P. (2021). Introduction of deep learning in thermographic monitoring of cultural heritage and improvement by automatic thermogram pre-processing algorithms. Sensors, 21.","DOI":"10.3390\/s21030750"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1021\/ar900193h","article-title":"New methodologies for the conservation of cultural heritage: Micellar solutions, microemulsions, and hydroxide nanoparticles","volume":"43","author":"Giorgi","year":"2010","journal-title":"Acc. Chem. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1134\/S1061830922010041","article-title":"Evaluating the efficiency of using ultraviolet radiation sources in carrying out fluorescent penetrant testing","volume":"58","author":"Kudinov","year":"2022","journal-title":"Russ. J. Nondestruct. Test."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"102804","DOI":"10.1016\/j.ndteint.2023.102804","article-title":"Automatic defect depth estimation for ultrasonic testing in carbon fiber reinforced composites using deep learning","volume":"135","author":"Cheng","year":"2023","journal-title":"NDT E Int."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fernandes, H., Summa, J., Daudre, J., Rabe, U., Fell, J., Sfarra, S., Gargiulo, G., and Herrmann, H.G. (2021). Characterization of ancient marquetry using different non-destructive testing techniques. Appl. Sci., 11.","DOI":"10.3390\/app11177979"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3835","DOI":"10.1007\/s10973-020-09326-2","article-title":"Evaluating quality of marquetries by applying active IR thermography and advanced signal processing","volume":"143","author":"Chulkov","year":"2021","journal-title":"J. Therm. Anal. Calorim."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1080\/17686733.2020.1799304","article-title":"Quantitative measurement of cast metal relics by pulsed thermal imaging","volume":"19","author":"Tao","year":"2022","journal-title":"Quant. InfraRed Thermogr. J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.infrared.2018.04.018","article-title":"Photothermal coherence tomography for 3-D visualization and structural non-destructive imaging of a wood inlay","volume":"91","author":"Tavakolian","year":"2018","journal-title":"Infrared Phys. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1111\/arcm.12653","article-title":"Combined use of infrared imaging techniques for the study of underlying features in the Santa Maria in Cosmedin altarpiece","volume":"63","author":"Mercuri","year":"2021","journal-title":"Archaeometry"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.ijthermalsci.2017.12.036","article-title":"Active thermography testing and data analysis for the state of conservation of panel paintings","volume":"126","author":"Yao","year":"2018","journal-title":"Int. J. Therm. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Md, A.Q., Kulkarni, S., Joshua, C.J., Vaichole, T., Mohan, S., and Iwendi, C. (2023). Enhanced preprocessing approach using ensemble machine learning algorithms for detecting liver disease. Biomedicines, 11.","DOI":"10.3390\/biomedicines11020581"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Md, A.Q., Jha, K., Haneef, S., Sivaraman, A.K., and Tee, K.F. (2022). A review on data-driven quality prediction in the production process with machine learning for industry 4.0. Processes, 10.","DOI":"10.3390\/pr10101966"},{"key":"ref_13","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_14","doi-asserted-by":"crossref","unstructured":"Milovanovi\u0107, B., Ga\u0161i, M., and Gumbarevi\u0107, S. (2020). Principal component thermography for defect detection in concrete. Sensors, 20.","DOI":"10.3390\/s20143891"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/j.infrared.2010.06.004","article-title":"A combined approach of self-referencing and principal component thermography for transient, steady, and selective heating scenarios","volume":"53","author":"Omar","year":"2010","journal-title":"Infrared Phys. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"12933","DOI":"10.1007\/s00500-021-06125-1","article-title":"Gait-based person fall prediction using deep learning approach","volume":"26","author":"Sampath","year":"2021","journal-title":"Soft Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s00521-020-05565-4","article-title":"Artificial neural networks and deep learning in the visual arts: A review","volume":"33","author":"Santos","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_18","unstructured":"Minaee, S., Liang, X., and Yan, S. (2022). Modern augmented reality: Applications, trends, and future directions. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"064006","DOI":"10.1088\/1361-6501\/ac5280","article-title":"Nondestructive detection and analysis based on data enhanced thermography","volume":"33","author":"Li","year":"2022","journal-title":"Meas. Sci. Technol."},{"key":"ref_20","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_21","doi-asserted-by":"crossref","unstructured":"Liu, K., Wang, F., He, Y., Liu, Y., Yang, J., and Yao, Y. (2022). Data-augmented manifold learning thermography for defect detection and evaluation of polymer composites. Polymers, 15.","DOI":"10.3390\/polym15010173"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6429","DOI":"10.1109\/TII.2022.3172902","article-title":"Deep autoencoder thermography for defect detection of carbon fiber composites","volume":"19","author":"Liu","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"115543","DOI":"10.1016\/j.compstruct.2022.115543","article-title":"IRT-GAN: A generative adversarial network with a multi-headed fusion strategy for automated defect detection in composites using infrared thermography","volume":"290","author":"Cheng","year":"2022","journal-title":"Compos. Struct."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"103754","DOI":"10.1016\/j.infrared.2021.103754","article-title":"Infrared machine vision and infrared thermography with deep learning: A review","volume":"116","author":"He","year":"2021","journal-title":"Infrared Phys. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"105382","DOI":"10.1016\/j.compbiomed.2022.105382","article-title":"Generative adversarial networks in medical image augmentation: A review","volume":"144","author":"Chen","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3527850","article-title":"Generative adversarial networks for face generation: A survey","volume":"55","author":"Kammoun","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"120711","DOI":"10.1016\/j.apenergy.2023.120711","article-title":"Federated-WDCGAN: A federated smart meter data sharing framework for privacy preservation","volume":"334","author":"Chen","year":"2023","journal-title":"Appl. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"112421","DOI":"10.1016\/j.measurement.2022.112421","article-title":"Fine-tuning transfer learning based on DCGAN Integrated with self-attention and spectral normalization for bearing fault diagnosis","volume":"210","author":"Zhong","year":"2023","journal-title":"Measurement"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TETCI.2022.3193373","article-title":"A new perspective on stabilizing GANs training: Direct adversarial training","volume":"7","author":"Li","year":"2022","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"104160","DOI":"10.1016\/j.infrared.2022.104160","article-title":"Micro-crack defects detection of semiconductor Si-wafers based on Barker code laser infrared thermography","volume":"123","author":"Bu","year":"2022","journal-title":"Infrared Phys. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ndteint.2016.09.002","article-title":"Quantitative validation of eddy current stimulated thermal features on surface crack","volume":"85","author":"Gao","year":"2017","journal-title":"NDT E Int."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.infrared.2017.07.012","article-title":"Ensemble variational bayes tensor factorization for super resolution of CFRP debond detection","volume":"85","author":"Lu","year":"2017","journal-title":"Infrared Phys. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6362\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:12:07Z","timestamp":1760127127000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,13]]},"references-count":32,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23146362"],"URL":"https:\/\/doi.org\/10.3390\/s23146362","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,13]]}}}