Selection of Scale-Invariant Parts for Object Class Recognition

  • Authors:
  • Gy. Dorkó;C. Schmid

  • Affiliations:
  • -;-

  • Venue:
  • ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper introduces a novel method for constructingand selecting scale-invariant object parts. Scale-invariantlocal descriptors are first grouped into basic parts. A classifieris then learned for each of these parts, and featureselection is used to determine the most discriminative ones.This approach allows robust part detection, and it is invariantunder scale change-that is, neither the training imagesnor the test images have to be normalized.The proposed method is evaluated in car detectiontasks with significant variations in viewing conditions, andpromising results are demonstrated. Different local regions,classifiers and feature selection methods are quantitativelycompared. Our evaluation shows that local invariantdescriptors are an appropriate representation for objectclasses such as cars, and it underlines the importance offeature selection.