Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

  • Authors:
  • Svetlana Lazebnik;Cordelia Schmid;Jean Ponce

  • 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 presents a framework for texture recognitionbased on local affine-invariant descriptors and their spatiallayout. At modeling time, a generative model of localdescriptors is learned from sample images using the EM algorithm.The EM framework allows the incorporation ofunsegmented multi-texture images into the training set. Thesecond modeling step consists of gathering co-occurrencestatistics of neighboring descriptors. At recognition time,initial probabilities computed from the generative modelare refined using a relaxation step that incorporates co-occurrencestatistics. Performance is evaluated on imagesof an indoor scene and pictures of wild animals.