Inter-image outliers and their application to image classification

  • Authors:
  • Alex Pappachen James;Sima Dimitrijev

  • Affiliations:
  • Griffith School of Engineering, Griffith University, QLD 4111, Australia;Griffith School of Engineering, Griffith University, QLD 4111, Australia

  • Venue:
  • Pattern Recognition
  • Year:
  • 2010

Quantified Score

Hi-index 0.01

Visualization

Abstract

Image variability that is impossible or difficult to restore by intra-image processing, such as the variability caused by occlusions, significantly reduces the performance of image-recognition methods. To address this issue, we propose that the pixels associated with large distances obtained by inter-image pixel-by-pixels comparisons should be considered as inter-image outliers and should be removed from the similarity calculation used for the image classification. When this method is combined with the template-matching method for image recognition, it leads to state-of-the-art recognition performance: 91% with AR database that includes occluded face images, 90% with PUT database that includes pose variations of face images and 100% with EYale B database that includes images with large illumination variation.