Affine-invariant local descriptors and neighborhood statistics for texture recognition
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 649-655 vol.1
- https://doi.org/10.1109/iccv.2003.1238409
Abstract
We present a framework for texture recognition based on local affine-invariant descriptors and their spatial layout. At modelling time, a generative model of local descriptors is learned from sample images using the EM algorithm. The EM framework allows the incorporation of unsegmented multitexture images into the training set. The second modelling 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.Keywords
This publication has 12 references indexed in Scilit:
- Man-made structure detection in natural images using a causal multiscale random fieldPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A sparse texture representation using affine-invariant regionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Viewpoint invariant texture matching and wide baseline stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Constructing models for content-based image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Indexing based on scale invariant interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Contour and Texture Analysis for Image SegmentationInternational Journal of Computer Vision, 2001
- Using spin images for efficient object recognition in cluttered 3D scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Texture-based image retrieval without segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Shape-adapted smoothing in estimation of 3-D shape cues from affine deformations of local 2-D brightness structureImage and Vision Computing, 1997
- Scene Labeling by Relaxation OperationsIEEE Transactions on Systems, Man, and Cybernetics, 1976