0508017 20241106135744.620190904235959.9 85072850585 10.1007/978-3-030-29888-3_32 7 s. P cav_un_epca*0508720978-3-030-29929-3402-408ChamSpringer2019VentoM.PercannellaG.ColantonioS.GiorgiD.MatuszewskiB. J.KerdegariH.RazaakM. Color image recognition Affine transformation Channel mixing Moment invariants Null-space cav_un_auth*0336802 Kostková Jitka 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. cav_un_auth*0101087 Flusser Jan 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/2019/ZOI/kostkova-0508017.pdf cav_un_auth*0360229 GA18-07247S GA ČR In this paper, we extend the theory of the combined Shape-Color Affine Moment Invariants (SCAMIs) for recognition of color images, proposed originally by Gong et al. in [3]. Since in the real pictures the shape deformation is always accompanied by the color deformation, it is not sufficient to use the shape invariant or color invariant descriptors only and the use of combined invariants is needed. However, the SCAMIs are not able to recognize images, the color channels of which are linearly dependent or highly correlated. This situation is not rare in practice and is of particular importance in hyper-spectral image analysis, where the spectral bands are highly correlated. We analyze why the SCAMIs fail in such situations, correct the theory and propose a solution to overcome such drawback. Unlike the SCAMIs, the new invariants have in the null-space the constant-zero images only, which leads to a better discrimination power, as demonstrated also on various pictures. cav_un_auth*0380252 International Conference on Computer Analysis of Images and Patterns, CAIP 2019 /18./ 20190902 20190906 Salerno IT JD 20000 20200 20206 2020 2 4 A sml 4as 20241106135744.6 PR RVO:67985556 http://hdl.handle.net/11104/0299554 S Consent to publish 20190528 Copyright 2019 Soubory v repozitáři: kostkova-0508017-Consent to publish.pdf 85072850585 SCOPUS PUBMED WOS cav_un_epca*0508720 Computer Analysis of Images and Patterns : CAIP 2019 International Workshops, ViMaBi and DL-UAV, Salerno, Italy, September 6, 2019, Proceedings Springer 2019 Cham 402 408 978-3-030-29929-3 Communications in Computer and Information Science 1089 340 Vento M. 340 Percannella G. 340 Colantonio S. 340 Giorgi D. 340 Matuszewski B. J. 340 Kerdegari H. 340 Razaak M.