In this report we describe “InnerSpec”, an approach for symmetric object detection that is based both on the com- putation of a symmetry measure for each pixel and on gra- dient information analysis. The symmetry value is obtained as the energy balance of the even-odd decomposition of an oriented square patch with respect to its central axis. Such an operation is akin to the computation of a row-wise con- volution in the midpoint. The candidate symmetry axes are then identified through the localization of peaks along the direction perpendicular to each considered angle. These axes are finally evaluated by computing the image gradient in their neighborhood, in particular checking whether the gradient information displays specular characteristics.
Innerspec: Technical Report
GUERRINI F.
Writing – Original Draft Preparation
;GNUTTI A.
Membro del Collaboration Group
;LEONARDI R.
Conceptualization
2017-01-01
Abstract
In this report we describe “InnerSpec”, an approach for symmetric object detection that is based both on the com- putation of a symmetry measure for each pixel and on gra- dient information analysis. The symmetry value is obtained as the energy balance of the even-odd decomposition of an oriented square patch with respect to its central axis. Such an operation is akin to the computation of a row-wise con- volution in the midpoint. The candidate symmetry axes are then identified through the localization of peaks along the direction perpendicular to each considered angle. These axes are finally evaluated by computing the image gradient in their neighborhood, in particular checking whether the gradient information displays specular characteristics.File | Dimensione | Formato | |
---|---|---|---|
GGL_ICCV-2017_full-text.pdf
accesso aperto
Descrizione: GGL_ICCV-2017_full-text
Tipologia:
Full Text
Licenza:
Creative commons
Dimensione
266.29 kB
Formato
Adobe PDF
|
266.29 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.