An axis-based representation for recognition


Creative Commons License

Aslan C., Tari S.

10th IEEE International Conference on Computer Vision (ICCV 2005), Beijing, China, 17 - 20 October 2005, pp.1339-1346 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iccv.2005.32
  • City: Beijing
  • Country: China
  • Page Numbers: pp.1339-1346

Abstract

We present a new axis-hased shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes.