Affine Moment Invariants of Tensor Fields

0571260 - ÚTIA 2024 RIV CH eng C - Konferenční příspěvek (zahraniční konf.)
Flusser, Jan - Suk, Tomáš - Lébl, Matěj - Bujack, R. - Ibrahim, I.
Affine Moment Invariants of Tensor Fields.
Image Analysis: 23rd Scandinavian Conference, SCIA 2023. Cham: Springer, 2023 - (Gade, R.), s. 299-313. Lecture notes on computer science, LNCS 13886. ISBN 978-3-031-31437-7.
[Scandinavian Conference on Image Analysis 2023 /23./. Levi (FI), 18.04.2023-21.04.2023]
Grant CEP: GA ČR GA21-03921S
Grant ostatní: AV ČR(CZ) StrategieAV21/1; GA MZd(CZ) IN 0002300
Program: StrategieAV
Institucionální podpora: RVO:67985556
Klíčová slova: Tensor field * affine invariants * template matching
Obor OECD: Computer hardware and architecture
http://library.utia.cas.cz/separaty/2023/ZOI/flusser-0571260.pdf

Tensor fields (TF) are a special kind of multidimensional data, in which a tensor is given for each point in space. Often, it is a 3 × 3 array in each voxel. To detect the patterns of interest in the field, special matching methods must be developed. We propose a method for the description and matching of TF patterns under an unknown affine transformation of the field. Transformations of TFs act not only in the spatial coordinates but also on the field values, which makes the detection more challenging. To measure the similarity between the template and the field patch, we propose original invariants with respect to affine transformations designed from moments. Their performance is demonstrated by experiments on real data from diffusion tensor imaging.
Trvalý link: https://hdl.handle.net/11104/0342936