TY - GEN
T1 - A graph representation for silhouette based on multiscale analysis
AU - Zhang, Ming Ming
AU - Omachi, Shinichiro
AU - Aso, Hirotomo
PY - 2009
Y1 - 2009
N2 - Graph descriptor is usually focused on in computer vision for its flexibility and richness. However, in object recognition, it is difficult to catch the feature of an object completely with a straightforward way by a graph. In this paper, from a multiscale viewpoint, we propose a method to construct a vertex-labeled graph for image recognition where the label represents the importance of a vertex to the graph. By using the Fourier Descriptor, when we adjust the cut-off frequency we can select how much detailed feature can be used to represent a contour. In this process, we found the medial axis of shape also evolves from a simple graph to a detailed graph. Focusing on this evolution, for each vertex in the graph we assign a label representing its importance in this graph.
AB - Graph descriptor is usually focused on in computer vision for its flexibility and richness. However, in object recognition, it is difficult to catch the feature of an object completely with a straightforward way by a graph. In this paper, from a multiscale viewpoint, we propose a method to construct a vertex-labeled graph for image recognition where the label represents the importance of a vertex to the graph. By using the Fourier Descriptor, when we adjust the cut-off frequency we can select how much detailed feature can be used to represent a contour. In this process, we found the medial axis of shape also evolves from a simple graph to a detailed graph. Focusing on this evolution, for each vertex in the graph we assign a label representing its importance in this graph.
KW - Fourier descriptor
KW - Graph recognition
KW - Graph representation
KW - Medial axis
KW - Multiscale analysis
KW - Silhouette image
UR - http://www.scopus.com/inward/record.url?scp=74549128681&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=74549128681&partnerID=8YFLogxK
U2 - 10.1109/CCPR.2009.5343992
DO - 10.1109/CCPR.2009.5343992
M3 - Conference contribution
AN - SCOPUS:74549128681
SN - 9781424441990
T3 - Proceedings of the 2009 Chinese Conference on Pattern Recognition, CCPR 2009, and the 1st CJK Joint Workshop on Pattern Recognition, CJKPR
SP - 837
EP - 839
BT - Proceedings of the 2009 Chinese Conference on Pattern Recognition, CCPR 2009, and the 1st CJK Joint Workshop on Pattern Recognition, CJKPR
T2 - 2009 Chinese Conference on Pattern Recognition, CCPR 2009 and the 1st CJK Joint Workshop on Pattern Recognition, CJKPR
Y2 - 4 November 2009 through 6 November 2009
ER -