International Journal of Computer Vision

, Volume 36, Issue 1, pp 31–50

Recognition without Correspondence using Multidimensional Receptive Field Histograms

  • Bernt Schiele
  • James L. Crowley
Article

DOI: 10.1023/A:1008120406972

Cite this article as:
Schiele, B. & Crowley, J.L. International Journal of Computer Vision (2000) 36: 31. doi:10.1023/A:1008120406972
  • 448 Views

Abstract

The appearance of an object is composed of local structure. This local structure can be described and characterized by a vector of local features measured by local operators such as Gaussian derivatives or Gabor filters. This article presents a technique where appearances of objects are represented by the joint statistics of such local neighborhood operators. As such, this represents a new class of appearance based techniques for computer vision. Based on joint statistics, the paper develops techniques for the identification of multiple objects at arbitrary positions and orientations in a cluttered scene. Experiments show that these techniques can identify over 100 objects in the presence of major occlusions. Most remarkably, the techniques have low complexity and therefore run in real-time.

object recognitionappearance based recognitionstatistical object representationlocal appearancereal-time computer vision

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Bernt Schiele
    • 1
  • James L. Crowley
    • 2
  1. 1.MIT Media LaboratoryCambridgeUSA
  2. 2.GRAVIR, INRIA Rhône–AlpesMonbonnotFrance