0576905 20240402214559.520231024235959.9 85179554546 10.1109/IPTA59101.2023.10319998 6 s. E cav_un_epca*0576904979-8-3503-2541-6PiscatawayIEEE2023 Neural network augmentation blur 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*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/2023/ZOI/flusser-0576905.pdf StrategieAV21/1 AV ČR CZ cav_un_auth*0328930 GA21-03921S GA ČR cav_un_auth*0412209 Neural networks are often trained on datasets, that are not fully representative of the expected query images. Many times, the difference stem from the query images being taken in sub-optimal conditions. The most common defects are rotation, scale, blur, noise and intensity & contrast change which were all thoroughly studied and described. In this paper we propose a novel neural network architecture which is invariant to such degradations by design. We incorporate the knowledge build for classical methods directly into the network architecture providing an alternative to the augmentation of the training dataset. In the experiments, the proposed solution outperforms the classical augmentation technique in both accuracy and computational resources needed. cav_un_auth*0456973 International Conference on Image Processing Theory, Tools and Applications (IPTA 2023) /12./ 20231016 20231019 Paris FR JD 20000 20200 20204 2024 2 PR RVO:67985556 https://hdl.handle.net/11104/0346495 S 10319998 2023 85179554546 SCOPUS PUBMED WOS cav_un_epca*0576904 Proceedings of The 12th International Conference on Image Processing Theory, Tools and Applications (IPTA 2023) IEEE 2023 Piscataway 979-8-3503-2541-6