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

Publications
Home  >  Research  >  Publications invariant featu

 
[International Journal] Object Recognition Using a Generalized Robust Invariant Feature and Gestalt's Law of Proximity and Similarity
Pattern Recognition , February 2008
Download
  shkim1.pdf shkim1.pdf (2.8M) [183]
Abstract
vol 41(2) / pp726-741

In this paper, we propose a new context-based method for object recognition. We first introduce a neuro-physiologically motivated visual part
detector. We found that the optimal form of the visual part detector is a combination of a radial symmetry detector and a corner-like structure
detector. A general context descriptor, named G-RIF (generalized-robust invariant feature), is then proposed, which encodes edge orientation,
edge density and hue information in a unified form. Finally, a context-based voting scheme is proposed. This proposed method is inspired
by the function of the human visual system, called figure-ground discrimination. We use the proximity and similarity between features to
support each other. The contextual feature descriptor and contextual voting method, which use contextual information, enhance the recognition
performance enormously in severely cluttered environments.

 
   
 

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