Key-components: detection of salient regions on 3D meshes
Author
dc.contributor.author
Sipiran, Iván
es_CL
Author
dc.contributor.author
Bustos Cárdenas, Benjamín
Admission date
dc.date.accessioned
2014-01-09T13:57:17Z
Available date
dc.date.available
2014-01-09T13:57:17Z
Publication date
dc.date.issued
2013
Cita de ítem
dc.identifier.citation
Vis Comput (2013) 29:1319–1332
en_US
Identifier
dc.identifier.other
DOI 10.1007/s00371-013-0870-9
Identifier
dc.identifier.uri
https://repositorio.uchile.cl/handle/2250/126102
General note
dc.description
Artículo de publicación ISI
en_US
Abstract
dc.description.abstract
In this paper, we present a method to detect stable
components on 3D meshes. A component is a salient
region on the mesh which contains discriminative local features.
Our goal is to represent a 3D mesh with a set of regions,
which we called key-components, that characterize
the represented object and therefore, they could be used for
effective matching and recognition. As key-components are
features in coarse scales, they are less sensitive to mesh deformations
such as noise. In addition, the number of keycomponents
is low compared to other local representations
such as keypoints, allowing us to use them in efficient subsequent
tasks. A desirable characteristic of a decomposition is
that the components should be repeatable regardless shape
transformations. We show in the experiments that the keycomponents
are repeatable and robust under several transformations
using the SHREC’2010 feature detection benchmark.
In addition, we discover the connection between the
theory of saliency of visual parts from the cognitive science
and the results obtained with our technique.