ArtInsight: A detailed dataset for detecting deterioration in easel paintings García Moreno, Francisco Manuel Del Castillo de la Fuente, José Manuel Rodríguez Simón, Luis Rodrigo Hurtado Torres, María Visitación Art restoration Damage detection Easel paintings Deep learning Mask-RCNN Image annotation Art dataset Digital preservation ArtInsight is an innovative dataset designed to detect dete- rioration in fine art, specifically easel paintings. The dataset includes high-resolution images captured at the University of Granada using a digital camera with a 105 mm lens, ISO 125, F5, and a shutter speed of 1/13, and processed for color cal- ibration. Two types of images are featured: those showing stucco technique interventions and those with Lacune from the loss of the Painting Layer (LPL). The VGG Image Annota- tor was employed for manual damage labeling, with annota- tions exported in JSON format and labeled for stucco and LPL damages. The dataset comprises 14 images with 2909 dis- tinct damage areas, split into training and validation datasets. Developed using Python 3.7 and fine-tuned on a pre-trained Mask-RCNN model, this dataset demonstrates high accuracy rates (98–100 %) in damage detection. ArtInsight aims to fa- cilitate automated damage detection and foster future research in art conservation and restoration. 2025-09-08T07:14:01Z 2025-09-08T07:14:01Z 2025-08 journal article F.M. Garcia-Moreno, J.M.d.C.d.l. Fuente and L.R. Rodríguez-Simón et al. / Data in Brief 61 (2025) 111811. https://doi.org/10.1016/j.dib.2025.111811 https://hdl.handle.net/10481/106117 10.1016/j.dib.2025.111811 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier