3D Object Recognition by Eigen-Scale-Space of Contours

11 years 5 months ago
3D Object Recognition by Eigen-Scale-Space of Contours
People often recognize 3D objects by their boundary shape. Designing an algorithm for such a task is interesting and useful for retrieving objects from a shape database. In this paper, we present a fast 2-stage algorithm for recognizing 3D objects using a new feature space, built from curvature scale space images, as a shape representation that is scale, translation, rotation and reflection invariant. As well, the new shape representation removes the inherent ambiguity of the zero position of arc length for a scale space image. The 2-stage matching algorithm, conducted in the eigenspaces of the feature space, is analogous to the way people recognize an object: first identifying the type of object, and then determining the actual object. We test the new algorithm on a 3D database comprising 209 colour objects in 2926 different view poses, and achieve a 97% recognition rate for the object type and 95% for the object pose.
Tim K. Lee, Mark S. Drew
Added 09 Jun 2010
Updated 09 Jun 2010
Type Conference
Year 2007
Authors Tim K. Lee, Mark S. Drew
Comments (0)