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

Publications
Home  >  Research  >  Publications biologically mo

 
[International Conference] Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature
Asian Conference on Computer Vision(ACCV) , January 2006
Download
  SunghoKim_ACCV2006_a.pdf SunghoKim_ACCV2006_a.pdf (356.0K) [65]
Abstract
In this paper, we present a new, biologically inspired perceptual
feature to solve the selectivity and invariance issue in object recognition.
Based on the recent findings in neuronal and cognitive mechanisms
in human visual systems, we develop a computationally efficient model.
An effective form of a visual part detector combines a radial symmetry
detector with a corner-like structure detector. A general context descriptor
encodes edge orientation, edge density, and hue information using a
localized receptive field histogram. We compare the proposed perceptual
feature (G-RIF: generalized robust invariant feature) with the state-ofthe-
art feature, SIFT, for feature-based object recognition. The experimental
results validate the robustness of the proposed perceptual feature
in object recognition.

 
 

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