0638746 20260213094752.920250909235959.9 10.1016/j.patcog.2025.112358 11 s. P cav_un_epca*02573880031-3203172Elsevier Color image Blur Invariants Image Recognition Cross-Channel invariants cav_un_auth*0457087 Košík Václav UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI CZ 50 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 40 K Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101209 Šroubek Filip UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing 10 Ústav teorie informace a automatizace AV ČR, v. v. i. https://library.utia.cas.cz/separaty/2025/ZOI/flusser-0638746.pdf https://www.sciencedirect.com/science/article/pii/S0031320325010192?via%3Dihub GA24-10069S GA ČR CZ cav_un_auth*0472834 The paper deals with the recognition of blurred color/multispectral images directly without any deblurring. We present a general theory of invariants of multispectral images with respect to blur. The paper is a significant nontrivial extension of the recent theory of blur invariants of graylevel images. The main original contribution of the paper lies in introducing cross-channel blur invariants in Fourier domain. We also developed an algorithm for their stable and fast calculation in the moment domain. Moreover, the cross-channel invariants can be found for blurs for which single-channel invariants do not exist. The experiments on simulated and real data demonstrate that incorporating the new cross-channel invariants significantly improves the recognition power and surpasses other existing approaches. The outlook for a possible implementation of the blur invariants into neural networks is briefly sketched in the conclusion. 2027 JD WOS 20000 20200 20204 3 RVO:67985556 https://hdl.handle.net/11104/0369335 S 112358 C COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE|ENGINEERING.ELECTRICAL&ELECTRONIC 7.9 1.2 4.9 0.04258 1.783 44785 257 2.058 46.37 9.84 19851 Q1 6.100 966 Q1 89.4 1.54 Q1 91.2 2026 SCOPUS PUBMED WOS cav_un_epca*0257388 Pattern Recognition 172 1 2026 0031-3203 1873-5142 Elsevier