Texel-based texture segmentation
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15505499), 841-848
- https://doi.org/10.1109/iccv.2009.5459308
Abstract
Given an arbitrary image, our goal is to segment all distinct texture subimages. This is done by discovering distinct, cohesive groups of spatially repeating patterns, called texels, in the image, where each group defines the corresponding texture. Texels occupy image regions, whose photometric, geometric, structural, and spatial-layout properties are samples from an unknown pdf. If the image contains texture, by definition, the image will also contain a large number of statistically similar texels. This, in turn, will give rise to modes in the pdf of region properties. Texture segmentation can thus be formulated as identifying modes of this pdf. To this end, first, we use a low-level, multiscale segmentation to extract image regions at all scales present. Then, we use the meanshift with a new, variable-bandwidth, hierarchical kernel to identify modes of the pdf defined over the extracted hierarchy of image regions. The hierarchical kernel is aimed at capturing texel substructure. Experiments demonstrate that accounting for the structural properties of texels is critical for texture segmentation, leading to competitive performance vs. the state of the art.Keywords
This publication has 27 references indexed in Scilit:
- Fast texture segmentation model based on the shape operator and active contourPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Lattice-Based MRF Model for Dynamic Near-Regular Texture TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- What are Textons?International Journal of Computer Vision, 2005
- Texture segmentation by multiscale aggregation of filter responses and shape elementsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Representing and Recognizing the Visual Appearance of Materials using Three-dimensional TextonsInternational Journal of Computer Vision, 2001
- Occlusion Models for Natural Images: A Statistical Study of a Scale-Invariant Dead Leaves ModelInternational Journal of Computer Vision, 2001
- Unsupervised texture segmentation in a deterministic annealing frameworkIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Computing texture boundaries from imagesNature, 1988
- Textons, the elements of texture perception, and their interactionsNature, 1981
- Statistical and structural approaches to textureProceedings of the IEEE, 1979