ARTDET: Machine learning software for automated detection of art deterioration in easel paintings García Moreno, Francisco Manuel Cortés Alcaráz, Jesús Del Castillo de la Fuente, José Manuel Rodríguez Simón, Luis Rodrigo Hurtado Torres, María Visitación Art conservation Machine learning Deterioration detection Cultural heritage Grant PID2023-149185OB-I00 funded by MICIU/AEI/ 10.13039/501100011033 and by ERDF/EU; and The Research Group Modelling & Development of Advanced Software Systems (TIC-230). The increasing interest in digital preservation of cultural heritage has led to ARTDET, a machine learning software for automated detection of deterioration in easel paintings. This web application uses a pre-trained Mask R-CNN model to detect Lacune (areas of missing paint, resulting in visible support panel) from the loss of the Painting Layer (LPL) and stucco repairs. ARTDET leverages high-resolution images annotated by expert restorers. The software achieved 80.4 % recall for LPL and stucco, with a 99 % confidence score in detected damages. Available as open access resource, ARTDET aids conservators and researchers in preserving invaluable artworks. 2025-09-08T07:24:39Z 2025-09-08T07:24:39Z 2024-12 journal article F.M. Garcia-Moreno et al. SoftwareX 28 (2024) 101917. https://doi.org/10.1016/j.softx.2024.101917 https://hdl.handle.net/10481/106118 10.1016/j.softx.2024.101917 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier