0490667 20240103220150.520180626235959.9 85049366167 000452025100058 10.1088/1757-899X/364/1/012058 8 s. E cav_un_epca*04906661757-8981PhiladelphiaIOP Science2018 NIR reflectograms VIS data DSLR cameras cav_un_auth*0254045 Blažek Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ K Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0361943 Vlašic O. CZ cav_un_auth*0101238 Zitová Barbara UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2018/ZOI/blazek-0490667.pdf cav_un_auth*0279441 LM2010005 GA MŠk CZ cav_un_auth*0361425 GA18-05360S GA ČR Features of Old Master paintings hidden under the upper layer of a painting are often studied using NIR reflectograms, however their interpretability can be reduced due to the visible content. In our previous work [3] we described the possibility of increasing the visibility of concealed features in NIR reflectograms from the painting surface. The method output, enhanced NIR reflectogram, is produced by extrapolating the VIS data to a NIR range reflectogram and subtracting it from the acquired data in the NIR spectral subband. As a result, separated information from the NIR domain is obtiained. This method has a severe limitation, because it requires precise image registration of the VIS and NIR spectral bands. This is often hard to achieve, because DSLR cameras or multiple devices with various optical systems are used for data collection, and the mutual spatial relation of the images is often unknown. Thus, in the original form ,the algorithm was applicable only for data acquired using special scanners producing spatially registered images (as in [4]). In this work, we present an extension of the previous algorithm inspired by deep learning. The new concept allows processing of images only partially registered with pixel precision, subpixel accuracy is no longer needed. We suggest an extension of neural network input with neighboring pixels and allocation of extra ANN layers for translation compensation. The results are demonstrated on misregistered images captured by DSLR camera in VIS and NIR. cav_un_auth*0361944 Florence Heri-Tech - The Future of Heritage Science and Technologies 20180516 20180518 Florence IT IN 10000 10200 10201 2019 PR RVO:67985556 http://hdl.handle.net/11104/0284818 1 cav_un_auth*0325763 Czech Technical University in Prague,Faculty of Nuclear Sciences and Physical Engineering ČVUT FJFI CZ S 012058 RIV/67985556:_____/18:00490667!RIV19-AV0-67985556 192095177 Doplnění UT WOS RIV/67985556:_____/18:00490667!RIV19-GA0-67985556 192084133 Doplnění UT WOS n.a. Proceedings Paper Archaeology|Architecture|Materials Science Multidisciplinary|Physics Applied|Imaging Science Photographic Technology 0.197 Q4 2018 85049366167 SCOPUS PUBMED 000452025100058 WOS cav_un_epca*0490666 Florence Heri-Tech - The Future of Heritage Science and Technologies 1757-8981 1757-899X Philadelphia IOP Science 2018 IOP Conference Series: Materials Science and Engineering Volume 364