Affine-invariant local descriptors and neighborhood statistics for texture recognition

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce

Research output: Contribution to conferencePaper

Abstract

This paper presents a framework for texture recognition based on local affine-invariant descriptors and their spatial layout. At modeling time, a generative model of local descriptors is learned from sample images using the EM algorithm. The EM framework allows the incorporation of unsegmented multi-texture images into the training set. The second modeling step consists of gathering co-occurrence statistics of neighboring descriptors. At recognition time, initial probabilities computed from the generative model are refined using a relaxation step that incorporates co-occurrence statistics. Performance is evaluated on images of an indoor scene and pictures of wild animals.

Original languageEnglish (US)
Pages649-655
Number of pages7
DOIs
StatePublished - 2003
EventProceedings: Ninth IEEE International Conference on Computer Vision - Nice, France
Duration: Oct 13 2003Oct 16 2003

Other

OtherProceedings: Ninth IEEE International Conference on Computer Vision
CountryFrance
CityNice
Period10/13/0310/16/03

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Affine-invariant local descriptors and neighborhood statistics for texture recognition'. Together they form a unique fingerprint.

  • Cite this

    Lazebnik, S., Schmid, C., & Ponce, J. (2003). Affine-invariant local descriptors and neighborhood statistics for texture recognition. 649-655. Paper presented at Proceedings: Ninth IEEE International Conference on Computer Vision, Nice, France. https://doi.org/10.1109/iccv.2003.1238409