Comparison of HK and SC Curvature Descriptions in a Scale-Space for the Purpose of 3D Object Recognition


IEEE 17th Signal Processing and Communications Applications Conference, Antalya, Turkey, 9 - 11 April 2009, pp.218-221 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2009.5136551
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.218-221


Most 3D object recognition methods use mean-Gaussian curvatures (HK) [2] or shape index-curvedness (SC) [3] values for classification. Although these two curvature descriptions classify objects into same categories, their mathematical definitions vary. In this study a comparion between the two curvature description is carried out for the purpose of 3D object recognition. Since unlike S; H, K and C values are not invariant of scale and resolution, a method to set them fully invariant to any transforation is proposed. The results show that scale and resolution invariant HK curvatire values gives better recognition results compared to SC curvature values.