Mgr. Tomáš Karella

Ph.D student

karella@utia.cas.cz 266052597 Personal web

Department: Department of Image Processing

Research interests: equivariant neural networks

Karella Tomáš, Suk Tomáš, Košík Václav, Bedratyuk L., Kerepecký Tomáš, Flusser Jan: 3D Non‑separable Moment Invariants and Their Use in Neural Networks, SN Computer Science 5 Download Download DOI: 10.1007/s42979-024-03504-x [2024]
Karella Tomáš, Blažek Jan, Striová J.: Convolutional neural network exploiting pixel surroundings to reveal hidden features in artwork NIR reflectograms, Journal of Cultural Heritage 58, p. 186-198 Download DOI: 10.1016/j.culher.2022.09.022 [2022]

Brom J., Assmann L., Kopeć M., Karella Tomáš, Blažek Jan: Způsob přesného 3D měření rozměrů a opotřebení komponent jaderných elektráren a zařízení k provádění tohoto způsobu (2024) Download [2024]
Karella Tomáš, Šroubek Filip, Blažek Jan, Flusser Jan, Košík Václav: H-NeXt: The next step towards roto-translation invariant networks, 34th British Machine Vision Conference 2023, p. 1-14 Download [2023]
Košík Václav, Karella Tomáš, Flusser Jan: CNN Ensemble Robust to Rotation Using Radon Transform, Proceedings of The 12th International Conference on Image Processing Theory, Tools and Applications (IPTA 2023) Download DOI: 10.1109/IPTA59101.2023.10320086 [2023]
Flusser Jan, Suk Tomáš, Bedratyuk L., Karella Tomáš: 3D Non-separable Moment Invariants, Computer Analysis of Images and Patterns. CAIP 2023, p. 295-305 Download DOI: 10.1007/978-3-031-44237-7_28 [2023]