2026-05-30T13:00:06Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/395312026-02-03T11:07:41Zcom_10630_2254col_10630_37953

00925njm 22002777a 4500 dc Stoean, Ruxandra author Bacanin, Nebojsa author Stoean, Catalin author Ionescu, Leonard author Atencia-Ruiz, Miguel Alejandro author Joya-Caparrós, Gonzalo author 2023 The accurate assessment of the material constitution and degradation in newly discovered archaeological artefacts is paramount for the decisions surrounding a thorough treatment of the object during the restoration and conservation stages. The laboratories possess competent experts and complex devices to perform this analysis properly. Nevertheless, a timely hint of an artificial intelligence assistant regarding the chemical composition and corrosion compound localization of a metal asset could save additional time and resources. The present paper proposes such a computational framework based on deep learning techniques that, on the base of its automatic determination of the chemical concentration of the predominant metal from a microscope image, can subsequently independently also recognize and delineate the corrosion spots of the products specific to that metal. The experiments have been performed on iron and copper heritage items from the Oltenia Museum, Romania. The results suggest that, even with an economic training information in terms of microscope images and annotations, the artificial intelligence framework can provide on-site support for an early examination of metal heritage assets. Ruxandra Stoean, Nebojsa Bacanin, Catalin Stoean, Leonard Ionescu, Miguel Atencia, Gonzalo Joya, Computational framework for the evaluation of the composition and degradation state of metal heritage assets by deep learning, Journal of Cultural Heritage, Volume 64, 2023, Pages 198-206 https://hdl.handle.net/10630/39531 10.1016/j.culher.2023.10.007 Arqueología - Metodología Aprendizaje automático (Inteligencia artificial) Computational framework for the evaluation of the composition and degradation state of metal heritage assets by deep learning