Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model

Lee, Tai Sing; Mumford, David; Yuille, Alan L.

doi:10.1007/3-540-55426-2_19

Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model

Tai Sing Lee, David Mumford, Alan L. Yuille

ECCV 1992 pp. 165-173

doi:10.1007/3-540-55426-2_19 /eccv/1992/lee1992eccv-texture/

Abstract

This paper presents a computational model that segments images based on the textural properties of object surfaces. The proposed Coupled-Membrane model applies the weak membrane approach to an image WI(σ,θ, x, y) , derived from the power responses of a family of selfsimilar quadrature Gabor wavelets. While segmentation breaks are allowed in x and y only, coupling is introduced to in all 4 dimensions. The resulting spatial and spectral diffusion prevents minor variations in local textures from producing segmentation boundaries. Experiments showed that the model is adequate in segmenting a class of synthetic and natural texture images.

PDF ECCV Semantic Scholar

Cite

Text

Lee et al. "Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_19

Markdown

[Lee et al. "Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/lee1992eccv-texture/) doi:10.1007/3-540-55426-2_19

BibTeX

@inproceedings{lee1992eccv-texture,
  title     = {{Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model}},
  author    = {Lee, Tai Sing and Mumford, David and Yuille, Alan L.},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {165-173},
  doi       = {10.1007/3-540-55426-2_19},
  url       = {https://mlanthology.org/eccv/1992/lee1992eccv-texture/}
}