0641413 20260226074344.120251112235959.9 105025053362 10.1109/IPTA66025.2025.11222047 6 s. E cav_un_epca*0641412978-1-6654-5739-22154-512XPiscatawayIEEE2025 color image blur invariants cross-channel invariants template matching cav_un_auth*0457087 Košík Václav 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*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. https://library.utia.cas.cz/separaty/2025/ZOI/flusser-0641413.pdf GA24-10069S GA ČR CZ cav_un_auth*0472834 The paper deals with the recognition of color images, blurred by N-fold symmetric out-of-focus blur, directly without any deblurring. We adopt the general theory of blur invariants of color images and modify it to this specific kind of blur. The main original contribution of the paper lies in introducing cross-channel blur invariants for N-fold symmetric kernels, which substantially improve the recognition power. The performance of the new invariants is illustrated by an experiment on blurred template matching. cav_un_auth*0496847 International Conference on Image Processing, Theory, Tools & Applications 2025 (IPTA 20025) /14./ 20251013 20251016 Istanbul TR JD 20000 20200 20204 2026 2 PR RVO:67985556 https://hdl.handle.net/11104/0371973 1 S 2025 105025053362 SCOPUS PUBMED WOS cav_un_epca*0641412 Proceedings of the Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA) 2025 IEEE 2025 Piscataway 978-1-6654-5739-2 2154-512X