In this work, the use of Information Geometry tools in Shape Analysis is investigated. Landmarks of complex shapes are represented as probability distributions in a statistical manifold where geodesics with respect to different Riemannian metrics could be defined. Geodesics are considered both for studying the shape evolution in time and for deriving shape distances to be used in shape clustering.
Information geometry tools for shape analysis
De Sanctis A.
;Gattone S. A.
2020-01-01
Abstract
In this work, the use of Information Geometry tools in Shape Analysis is investigated. Landmarks of complex shapes are represented as probability distributions in a statistical manifold where geodesics with respect to different Riemannian metrics could be defined. Geodesics are considered both for studying the shape evolution in time and for deriving shape distances to be used in shape clustering.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
nlcsig-2020.pdf
accesso aperto
Tipologia:
PDF editoriale
Dimensione
1.13 MB
Formato
Adobe PDF
|
1.13 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.