Inter-image outliers and their application to image classification

Alex Pappachen James, Sima Dimitrijev

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)


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.

Original languageEnglish
Pages (from-to)4101-4112
Number of pages12
JournalPattern Recognition
Issue number12
Publication statusPublished - Dec 2010


  • Image recognition
  • Outliers
  • Template matching

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Inter-image outliers and their application to image classification'. Together they form a unique fingerprint.

Cite this