Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature

  • Sungho Kim
  • In So Kweon
Conference paper

DOI: 10.1007/11612704_31

Part of the Lecture Notes in Computer Science book series (LNCS, volume 3852)
Cite this paper as:
Kim S., Kweon I.S. (2006) Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature. In: Narayanan P.J., Nayar S.K., Shum HY. (eds) Computer Vision – ACCV 2006. ACCV 2006. Lecture Notes in Computer Science, vol 3852. Springer, Berlin, Heidelberg

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-of-the-art feature, SIFT, for feature-based object recognition. The experimental results validate the robustness of the proposed perceptual feature in object recognition.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sungho Kim
    • 1
  • In So Kweon
    • 1
  1. 1.Dept. of EECSKorea Advanced Institute of Science and TechnologyDaejeonKorea

Personalised recommendations