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

Publications
Home  >  Research  >  Publications invariant featu

 
[Domestic Conference] P-RIF: Perceptually Robust Invariant Feature
IPIU , February 2013
Download
  IPIU2013_shkim_O-017.pdf IPIU2013_shkim_O-017.pdf (252.0K) [46]
Abstract
We present a new visual encoding method for object recognition. According to the neuro-physiological findings, 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 encodes the curvature as well as the dominant orientation which enhance
the performance of feature matching and object recognition taken from standard test images. The results from the
repeatability and object recognition tests validate the feasibility of the proposed P-RIF.

 
 
 

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