Ink classification in historical documents using hyperspectral imaging and machine learning methods López Baldomero, Ana Belén Buzzelli, Marco Moronta-Montero, Francisco Martínez Domingo, Miguel Ángel Valero Benito, Eva María Ink classification historical documents hyperspectral imaging material identification machine learning approach data fusion cultural heritage This work was supported by Ministry of Universities (Spain) [grant number FPU2020-05532], by MCIN/AEI/10.13039/501100011033, by “ERDF A way of making Europe” [grant number PID2021-124446NB-100], and by “ESF Investing in your future” [grant number PRE2022-101352]. This work was partially supported by the Italian Ministry for Universities and Research (MUR) (Italy) under the grant “Dipartimenti di Eccellenza 2023-2027” of the Department of Informatics, Systems and Communication of the University of Milano-Bicocca, Italy. Ink identification using only spectral reflectance information poses significant challenges due to material degradation, aging, and spectral overlap between ink classes. This study explores the use of hyperspectral imaging and machine learning techniques to classify three distinct types of inks: pure metallo-gallate, carbon-containing, and non-carbon-containing inks. Six supervised classification models, including five traditional algorithms (Support Vector Machines, K-Nearest Neighbors, Linear Discriminant Analysis, Random Forest, and Partial Least Squares Discriminant Analysis) and one Deep Learning-based model, were evaluated. The methodology integrates data fusion from different imaging systems, sample extraction, ground truth creation, and a post-processing step to increase uniformity. The evaluation was performed using both mock-up samples and historical documents, achieving micro-averaged accuracy above 90% for all models. The best performance was obtained using the DL-based model (98% F1-score), followed by the Support Vector Machine model. In the case study documents, the overall performance of the traditional model was better. This study highlights the potential of hyperspectral imaging combined with machine learning for non-invasive ink identification and mapping, even under challenging conditions, contributing to the conservation and analysis of historical manuscripts. 2025-04-03T06:25:31Z 2025-04-03T06:25:31Z 2025-02 journal article López-Baldomero, A. B. et al. (2025). Ink classification in historical documents using hyperspectral imaging and machine learning methods. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 125916. https://doi.org/10.1016/j.saa.2025.125916 https://hdl.handle.net/10481/103408 10.1016/j.saa.2025.125916 eng Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy; http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier