Robust multi-TAR of barycenter contour for multiple views shape matching and retrieval

Simple item page
dc.contributor.authorThourn, Kosorl
dc.contributor.authorKitjaidure, Yuttana
dc.date.accessioned2026-08-06T09:56:17Z
dc.date.available2026-08-06T09:56:17Z
dc.date.issued2008-01-01
dc.description.abstractIn this paper, we present a one dimensional descriptor for the two dimensional object silhouettes associated with each level of barycenter contour for multiple views shape matching and retrieval. Firstly, the barycenter contour is applied onto the shape contour. Then the averaging multitriangle area representation (AMTAR) at each level of barycenter contour is computed as the shape descriptor. Finally, to classify among the shapes, the normalized crosscorrelation function is used. Our algorithm is implemented on database consisting of 560 affine distorted shapes, chosen from MPEG-7 contour shape database CE-1. The experimental results indicate that the proposed method is invariant to affine transformation, robustness to the noise, and achieves high retrieval performance. © 2008 IEEE.
dc.identifier.citation2008 IEEE International Conference on Robotics and Biomimetics Robio 2008, 1894-1898, 2008
dc.identifier.doi10.1109/ROBIO.2009.4913290
dc.identifier.other2-s2.0-70349190065
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/1915
dc.source2008 IEEE International Conference on Robotics and Biomimetics Robio 2008
dc.subjectAffine transformation
dc.subjectAveraging multi-triangle area representation (AMTAR)
dc.subjectBarycenter contour
dc.titleRobust multi-TAR of barycenter contour for multiple views shape matching and retrieval
dc.typeConference Paper

Files

Collections

Research