An original solution for shape representation is proposed which relies on a spatial partitioning approach. The representation selects a discrete set of reference points with respect to which a relationship matrix is computed, accounting for the spatial distribution of shape pixels. This is accomplished at different levels of resolution by a tree based representation. Depending on the number of points, coarse to fine region and boundary shape information are captured. Properties of the representation are discussed and assessed through an experimental evaluation on a set of sample shapes.
MULTIRESOLUTION SPATIAL PARTITIONING FOR SHAPE REPRESENTATION / S. BERRETTI; A. DEL BIMBO. - STAMPA. - (2004), pp. 775-778. (Intervento presentato al convegno ICPR04, IEEE INT. CONF. ON PATTERN RECOGNITION tenutosi a CAMBRIDGE, UK nel August, 23-26) [10.1109/ICPR.2004.1334373].
MULTIRESOLUTION SPATIAL PARTITIONING FOR SHAPE REPRESENTATION
BERRETTI, STEFANO;DEL BIMBO, ALBERTO
2004
Abstract
An original solution for shape representation is proposed which relies on a spatial partitioning approach. The representation selects a discrete set of reference points with respect to which a relationship matrix is computed, accounting for the spatial distribution of shape pixels. This is accomplished at different levels of resolution by a tree based representation. Depending on the number of points, coarse to fine region and boundary shape information are captured. Properties of the representation are discussed and assessed through an experimental evaluation on a set of sample shapes.
| File | Dimensione | Formato | |
|---|---|---|---|
|
icpr04.pdf
Accesso chiuso
Descrizione: documento finale
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
Tutti i diritti riservati
Dimensione
328.83 kB
Formato
Adobe PDF
|
328.83 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
