Global and efficient self-similarity for object classification and detection

T. Deselaers, V. Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Self-similarity is an attractive image property which has recently found its way into object recognition in the form of local self-similarity descriptors. In this paper we explore global self-similarity (GSS) and its advantages over local self-similarity (LSS). We make three contributions: (a) we propose computationally efficient algorithms to extract GSS descriptors for classification. These capture the spatial arrangements of self-similarities within the entire image; (b) we show how to use these descriptors efficiently for detection in a sliding-window framework and in a branch-and-bound framework; (c) we experimentally demonstrate on Pascal VOC 2007 and on ETHZ Shape Classes that GSS outperforms LSS for both classification and detection, and that GSS descriptors are complementary to conventional descriptors such as gradients or color.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
ISBN (Print)978-1-4244-6984-0
Publication statusPublished - 1 Jun 2010

Keywords / Materials (for Non-textual outputs)

  • object detection
  • object recognition
  • pattern classification
  • tree searching
  • GSS
  • LSS
  • branch-and-bound framework
  • global self similarity
  • image property
  • local self similarity
  • object classification
  • sliding window framework
  • Algorithm design and analysis
  • Computer vision
  • Gas detectors
  • Histograms
  • Hypercubes
  • Laboratories
  • Object detection
  • Object recognition
  • Pixel
  • Shape


Dive into the research topics of 'Global and efficient self-similarity for object classification and detection'. Together they form a unique fingerprint.

Cite this