0562826 20250310153141.520221024235959.9 85140310447 000877579300006 10.1016/j.culher.2022.09.022 13 s. P cav_un_epca*02583471296-207458186-198Elsevier Signal separation Concealed features visualization Artwork analysis Infrared reflectography Convolutional neural networks cav_un_auth*0438860 Karella Tomáš UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0254045 Blažek Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0340366 Striová J. IT https://www.sciencedirect.com/science/article/pii/S1296207422001637?via%3Dihub GA21-03921S GA ČR cav_un_auth*0412209 StrategieAV21/1 AV ČR CZ cav_un_auth*0328930 Near-infrared reflectography (NIR) is a well-established non-invasive and non-contact imaging technique. The NIR methods are able to reveal concealed layers of artwork, such as a painter’s sketch or repainted canvas. The information obtained may be helpful to historians for studying artist technique, attributing an artwork reconstructing faded details. Our research presents the improved method previously developed that reveals the hidden features by removing the information content of the visible spectrum from NIR. Based on convolutional neural networks (CNN), our model estimates the transfer function from visible spectra to NIR, which is nonlinear and specific for painting materials. Its parameters are learnt for particular paintings on the subsamples randomly selected across the canvas, and the model is further utilised to enhance the whole artwork. In addition to the previously developed model, our algorithm exploits each pixel’s surroundings to estimate its NIR response. This leads to more precise results and increased robustness to various noises. We demonstrate higher accuracy than the previous method on the historical paintings mock-ups and higher performance on well-known artworks such as Madonna dei Fusi attributed to Leonardo da Vinci. WOS JC 20000 20200 20206 2023 3 2 R hod 4 4rh 4 20250310152814.4 4 20250310153141.5 RVO:67985556 https://hdl.handle.net/11104/0335176 cav_un_auth*0438861 National Research Council (CNR), National Institute of Optics (INO) IT S 3+4 Article Archaeology|Art|Chemistry Analytical|Geosciences Multidisciplinary|Materials Science Multidisciplinary|Spectroscopy C MATERIALSSCIENCE.MULTIDISCIPLINARY|GEOSCIENCES.MULTIDISCIPLINARY|CHEMISTRY.ANALYTICAL|ART|ARCHAEOLOGY|SPECTROSCOPY 3.2 0.8 5.9 0.00444 0.585 5595 0.699 2.800 154 60 Q3 Q2 2.1 Q1 72 2022 Soubory v repozitáři: karella-562826.pdf 85140310447 SCOPUS PUBMED 000877579300006 WOS cav_un_epca*0258347 Journal of Cultural Heritage 1296-2074 1778-3674 Roč. 58 November–December 2022 186 198 Elsevier