We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types.
SymPaD: Symbolic patch descriptor / S. Aslan, C.B. Akgul, B. Sankur, E.T. Tunali (VISIGRAPP). - In: Proceedings of the 10th International Conference on Computer Vision Theory and Applications VISIGRAPP. 2 / [a cura di] J. Braz, S. Battiato, F. Imai. - [s.l] : SciTePress, 2015. - ISBN 978-989-758-089-5. - pp. 266-271 (( Intervento presentato al 10. convegno International Conference on Computer Vision Theory and Applications tenutosi a Berlin nel 2015 [10.5220/0005361802660271].
SymPaD: Symbolic patch descriptor
S. Aslan
Primo
;
2015
Abstract
We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types.
| File | Dimensione | Formato | |
|---|---|---|---|
|
aslan2015_VISAPP.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
398.03 kB
Formato
Adobe PDF
|
398.03 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
