0573978 20250310153135.320230731235959.9 85160864192 001000360800003 10.1007/s11263-023-01798-7 18 s. P cav_un_epca*02533630920-56911319 (2023)2298-2315Springer Blurred image Object recognition Blur invariants Projection operators Moments 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. cav_un_auth*0377447 Lébl Matěj 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*0101209 Šroubek Filip 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*0389933 Pedone M. FI 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. http://library.utia.cas.cz/separaty/2023/ZOI/flusser-0573978.pdf https://link.springer.com/article/10.1007/s11263-023-01798-7 GA21-03921S GA ČR cav_un_auth*0412209 Blur is an image degradation that makes object recognition challenging. Restoration approaches solve this problem via image deblurring, deep learning methods rely on the augmentation of training sets. Invariants with respect to blur offer an alternative way of describing and recognising blurred images without any deblurring and data augmentation. In this paper, we present an original theory of blur invariants. Unlike all previous attempts, the new theory requires no prior knowledge of the blur type. The invariants are constructed in the Fourier domain by means of orthogonal projection operators and moment expansion is used for efficient and stable computation. Applying a general substitution rule, combined invariants to blur and spatial transformations are easy to construct and use. Experimental comparison to Convolutional Neural Networks shows the advantages of the proposed theory. WOS JD 20000 20200 20204 2024 5 2 R hod 4 4rh 4 20250310152908.7 4 20250310153135.3 RVO:67985556 https://hdl.handle.net/11104/0344425 cav_un_auth*0349870 University of Oulu FI S Article Computer Science Artificial Intelligence A COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE 14.5 0.8 8.4 0.02469 4.486 25505 232 6.668 72.52 17.4 8969 Q1 11.200 198 Q1 96.7 Q1* Q1* 2.82 Q1 96.7 2023 Soubory v repozitáři: flusser-0573978.pdf 85160864192 SCOPUS PUBMED 001000360800003 WOS cav_un_epca*0253363 International Journal of Computer Vision 0920-5691 1573-1405 Roč. 131 č. 9 2023 2298 2315 Springer