TY - GEN
T1 - Key-component detection on 3D meshes using local features
AU - Sipiran, Ivan
AU - Bustos, Benjamin
PY - 2012
Y1 - 2012
N2 - In this paper, we present a method to detect stable components on 3D meshes. A component is a 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 key-components is low compared to other local representations such as keypoints, allowing us to use them in efficient subsequent tasks. An desirable characteristic of a decomposition is that the components should be repeatable regardless shape transformations. We show in the experiments that the key-components are repeatable under several transformations using the SHREC'2010 feature detection benchmark.
AB - In this paper, we present a method to detect stable components on 3D meshes. A component is a 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 key-components is low compared to other local representations such as keypoints, allowing us to use them in efficient subsequent tasks. An desirable characteristic of a decomposition is that the components should be repeatable regardless shape transformations. We show in the experiments that the key-components are repeatable under several transformations using the SHREC'2010 feature detection benchmark.
UR - http://www.scopus.com/inward/record.url?scp=84883528696&partnerID=8YFLogxK
U2 - 10.2312/3DOR/3DOR12/025-032
DO - 10.2312/3DOR/3DOR12/025-032
M3 - Conference contribution
AN - SCOPUS:84883528696
SN - 9783905674361
T3 - Eurographics Workshop on 3D Object Retrieval, EG 3DOR
SP - 25
EP - 32
BT - EG 3DOR 2012 - Eurographics 2012 Workshop on 3D Object Retrieval
T2 - 5th Eurographics Workshop on 3D Object Retrieval, EG 3DOR 2012
Y2 - 13 May 2012 through 13 May 2012
ER -