Robotics and Computer Vision Laboratory Login  
  Robotics and Computer Vision Laboratory kaist logo
Archive Courses

Home  >  Research  >  Publications

[Domestic Conference]
ڰȸ ߰нȸ , September 2011
  _IEEK2011_11_輺ȣ.pdf _IEEK2011_11_輺ȣ.pdf (2.2M) [82]
In this paper, we propose a new shape encoding method for object recognition. We first introduce a neuro‐physiologically motivated visual part detector and shape encoder. We found that the optimal form of the visual part detector is a combination of a circular symmetry detector and a corner‐like structure detector. A perceptually novel shape descriptor, named curvature‐orientation descriptor, is then proposed, which encodes curvature as well as dominant orientation. The perceptual shape<BR>encoder enhances the feature matching performance enormously in the standard test images.


Robotics and Computer Vision Laboratory
KAIST | Electrical Engineering | Contact Us | Sitemap