Ing. Václav Košík
Ph.D student
Department:
Department of Image Processing
Research interests:
Neural networks, invariant description, numerical methods
Biography
Publication list
Václav Košík received the M.Sc. degree in mathematical modelling from the Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University, Prague, in 2020 with the master’s thesis focused on combinatorics on words. He is currently pursuing PhD with research interest in image invariants and neural networks that are equivariant/invariant to various image transformations.
Journal articles
- : Cross-Channel Blur Invariants of Color and Multispectral Images, Pattern Recognition 172 Download Download DOI: 10.1016/j.patcog.2025.112358 [2026]
- : 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]
Other publications
- : Invariants of Color Images to N-Fold Symmetric Out-of-Focus Blur, Proceedings of the Fourteenth International Conference on Image Processing, Theory, Tools & Applications (IPTA) 2025 Download DOI: 10.1109/IPTA66025.2025.11222047 [2025]
- : Atmospheric microplastics modelling and quantification using Gibbs sampler, Abstract Book of European Aerosol Conference 2025 (EAC 2025) Download [2025]
- : Atmospheric microplastics emissions estimation and uncertainty quantification using Gibbs sampler, EGU General Assembly 2025 Download DOI: 10.5194/egusphere-egu25-11924 [2025]
- : H-NeXt: The next step towards roto-translation invariant networks, 34th British Machine Vision Conference 2023, p. 1-14 Download [2023]
- : 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]