Number of the records: 1
3D Non-separable Moment Invariants
- 1.0575788 - ÚTIA 2024 RIV CH eng C - Conference Paper (international conference)
Flusser, Jan - Suk, Tomáš - Bedratyuk, L. - Karella, Tomáš
3D Non-separable Moment Invariants.
Computer Analysis of Images and Patterns. CAIP 2023. Cham: Springer, 2023 - (Tsapatsoulis, N.), s. 295-305. Lecture Notes in Computer Science, 14184. ISBN 978-3-031-44236-0.
[Computer Analysis of Images and Patterns. CAIP 2023. Limassol (CY), 25.09.2023-28.09.2023]
R&D Projects: GA ČR GA21-03921S
Institutional support: RVO:67985556
Keywords : 3D recognition * 3D rotation invariants * non-separable moments * Appell polynomials
OECD category: Computer hardware and architecture
http://library.utia.cas.cz/separaty/2023/ZOI/flusser-0575788.pdf
In this paper, we introduce new 3D rotation moment invariants, which are composed of non-separable Appell moments. The Appell moments can be substituted directly into the 3D rotation invariants instead of the geometric moments without violating their invariance. We show that non-separable moments may outperform the separable ones in terms of recognition power and robustness thanks to a better distribution of their zero surfaces over the image space. We test the numerical properties and discrimination power of the proposed invariants on three real datasets – MRI images of human brain, 3D scans of statues, and confocal microscope images of worms.
Permanent Link: https://hdl.handle.net/11104/0345843
Number of the records: 1