Content deleted Content added
Seliseli88 (talk | contribs) No edit summary |
Declining submission: submission is unsourced or contains only unreliable sources (AFCH) |
||
Line 1:
{{AFC submission|d|v|declinets=20140107181649|decliner=Puffin|ts=20140107174419|u=Seliseli88|ns=
{{FeatureDetectionCompVisNavbox}}
▲{{AFC submission|||ts=20140107174419|u=Seliseli88|ns=2}}
Generalized Structure Tensor is an extension of the Cartesian [[Structure Tensor]] to [[Curvilinear coordinates]]. It finds the direction along which an image can undergo a translation with minimal error, measured in [[L2 norm]] amounting to [[total least squares]] sense, where the translation is along the curvilinear coordinates (instead of Cartesian).
Among the curvilinear coordinates, locally orthogonal coordinates, are best studied.<ref name=bigun86>
@inproceedings{bigun1988pattern,
title="Pattern recognition by detection of local symmetries",
Line 22 ⟶ 14:
The Generalized structure tensor can be used as an alternative to [[Hough Transform]] in [[image processing]] and [[computer vision]]. The main differences comprise:
*Negative voting is allowed
*With one template multiple patterns belonging to the same family can be detected, because not nonly negative but also Complex Voting is allowed.
== See also ==▼
▲==See also==
*[[Hough Transform]]
*[[Tensor]]
Line 36 ⟶ 27:
*[[Affine shape adaptation]]
== References ==▼
{{reflist}}
▲==References==
== Resources ==
{{DEFAULTSORT:Generalized Structure Tensor}}
[[:Category:Tensors]]
[[:Category:Feature detection]]
|