Abstract
This work comprehensively reviews artificial intelligence (AI) methods for macroscopic X-ray fluorescence (MA-XRF) data analysis of a religious panel painting (icon). ΜΑ-XRF is a powerful analytical imaging technique used to determine the elemental distribution maps of inhomogeneous targets. For the data analysis, we apply clustering algorithms such as k-means, factorization methods such as principal component analysis (PCA) and non-negative matrix factorization (NMF), and basic supervised machine learning methods, such as k-nearest neighbor (k-NN) regression and multilayer perceptron (MLP) regression. The applied AI methods allow for detailed and fast data analysis, providing two-dimensional elemental maps. The methods are beneficial for inexperienced users as they can analyze the MA-XRF data without detailed knowledge of the involved physics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mantler M, Schreiner M (2000) X-ray fluorescence spectrometry in art and archaeology. X-Ray Spectrom: Int J 29(1):3–17
Janssens K, Van der Snickt G, Vanmeert F, Legrand S, Nuyts G, Alfeld M, Monico L, Anaf W, De Nolf W, Vermeulen M, Verbeeck J, De Wael K (2016) Non-invasive and non-destructive examination of artistic pigments, paints, and paintings by means of X-ray methods. Top Curr Chem 374(81). https://doi.org/10.1007/s41061-016-0079-2
Romano FP, Caliri C, Nicotra P, Di Martino S, Pappalardo L, Rizzo F, Santos HC (2017) Real-time elemental imaging of large dimension paintings with a novel mobile macro X-ray fluorescence (MA-XRF) scanning technique. J Anal At Spectrom 32:773–781
Alfeld M, Mösl K, Reiche I (2021) Sunset and moonshine: variable blue and yellow pigments used by Caspar David Friedrich in different creative periods revealed by in situ XRF imaging. X-Ray Spectrom 50(4):341–350
Delaney JK, Dooley KA, Van Loon A, Vandivere A (2020) Mapping the pigment distribution of Vermeer’s Girl with a Pearl Earring. Herit Sci 8(1):1–16
Saverwyns S, Currie C, Lamas-Delgado E (2018) Macro X-ray fluorescence scanning (MA-XRF) as tool in the authentication of paintings. Microchem J 137:139–147
Shugar A (2021) Advancements in portable and lab based XRF instrumentation for analysis in cultural heritage: a change in perspective. Microsc Microanal 27(S1):2552–2553
Xu BJ, Wu Y, Hao P, Vermeulen M, McGeachy A, Smith K, Walton M et al (2022) Can deep learning assist automatic identification of layered pigments from XRF data?. J Anal At Spectrom 37(12):2672–2682
Chopp H, McGeachy A, Alfeld M, Cossairt O, Walton M, Katsaggelos A (2022) Image processing perspectives of X-ray fluorescence data in cultural heritage sciences. IEEE BITS Inf Theory Mag 2(1):20–35
Kogou S, Lee L, Shahtahmassebi G, Liang H (2021) A new approach to the interpretation of XRF spectral imaging data using neural networks. X-Ray Spectrom 50(4):310–319
Gerodimos T, Asvestas A, Mastrotheodoros GP, Chantas G, Liougos I, Likas A, Anagnostopoulos DF (2022) Scanning X-ray fluorescence data analysis for the identification of byzantine icons’ materials, techniques, and state of preservation: a case Study. J Imaging 8(5):147
Alfeld M, Pedroso JV, van Eikema Hommes M, Van der Snickt G, Tauber G, Blaas J, Janssens K (2013) A mobile instrument for in situ scanning macro-XRF investigation of historical paintings. J Anal At Spectrom 28(5):760–767
Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdiscip Rev: Comput Statis 2(4):433–459
Łach B, Fiutowski T, Koperny S, Krupska-Wolas P, Lankosz M, Mendys-Frodyma A, Dąbrowski W et al (2021) Application of factorisation methods to analysis of elemental distribution maps acquired with a full-field XRF imaging spectrometer. Sensors 21(23):7965
Cichocki A, Phan AH (2009) Fast local algorithms for large-scale nonnegative matrix and tensor factorizations. IEICE Trans Fundam Electron Commun Comput Sci 92(3):708–721
Alfeld M, Wahabzada M, Bauckhage C, Kersting K, Wellenreuther G, Falkenberg G (Apr 2014) Non-negative factor analysis supporting the interpretation of elemental distribution images acquired by XRF. In: Journal of physics: conference series, vol 499, no 1. IOP Publishing, p 012013
Magkanas G, Bagán H, Sistach MC, García JF (2021) Illuminated manuscript analysis methodology using MA-XRF and NMF: application on the Liber Feudorum Maior. Microchem J 165:106112
Mihalić IB, Fazinić S, Barac M, Karydas AG, Migliori A, Doračić D, Krstić D et al (2021) Multivariate analysis of PIXE+XRF and PIXE spectral images. J Anal At Spectrom 36(3):654–667
Orsilli J, Galli A, Bonizzoni L, Caccia M (2021) More than XRF mapping: STEAM (Statistically Tailored Elemental Angle Mapper) a pioneering analysis protocol for pigment studies. Appl Sci 11:1446
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Duchesnay E et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Solé VA, Papillon E, Cotte M, Walter P, Susini J (2007) A multiplatform code for the analysis of energy-dispersive X-ray fluorescence spectra. Spectrochim Acta Part B: AtIc Spectrosc 62(1):63–68
MacQueen J (1967) Classification and analysis of multivariate observations. In: 5th Berkeley symposium on mathematical statistics and probability, pp 281–297
Likas A, Vlassis N, Verbeek JJ (2003) The global k-means clustering algorithm. Pattern Recogn 36(2):451–461
Mastrotheodoros GP, Beltsios KG, Bassiakos Y, Papadopoulou V (2016) On the grounds of post-byzantine Greek icons. Archaeometry 58(5):830–847
Kühn H, Curran M (1986) Chrome yellow and other chromate pigments. In: Feller RL (ed)Artist’s pigments: a handbook of their history and characteristics. National Gallery of Art, Cambridge University Press: Cambridge, UK, pp 186–217
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Acknowledgements
This research was supported by project “Dioni: Computing Infrastructure for Big-Data Processing and Analysis” (MIS No. 5047222) co-funded by European Union (ERDF) and Greece through Operational Program “Competitiveness, Entrepreneurship and Innovation”, NSRF 2014–2020.
Special thanks are due to M. Ziagkos for providing access to icon from private collection.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gerodimos, T. et al. (2024). Artificial Intelligence Analysis of Macroscopic X-Ray Fluorescence Data: A Case Study of Nineteenth Century Icon. In: Osman, A., Moropoulou, A., Lampropoulos, K. (eds) Advanced Nondestructive and Structural Techniques for Diagnosis, Redesign and Health Monitoring for the Preservation of Cultural Heritage. TMM 2023. Springer Proceedings in Materials, vol 33. Springer, Cham. https://doi.org/10.1007/978-3-031-42239-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-42239-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42238-6
Online ISBN: 978-3-031-42239-3
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)