Normalized Texture Motifs and Their Application to Statistical Object Modeling

CVPR 2004 pp. 45

doi:10.1109/CVPR.2004.408 /cvpr/2004/newsam2004cvpr-normalized/

Abstract

A fundamental challenge in applying texture features to statistical object modeling is recognizing differently oriented spatial patterns. Rows of moored boats in remote sensed images of harbors should be consistently labeled regardless of the orientation of the harbors, or of the boats within the harbors. This is not straightforward to do, however, when using anisotropic texture features to characterize the spatial patterns. We here propose an elegant solution, termed normalized texture motifs, that uses a parametric statistical model to characterize the patterns regardless of their orientation. The models are learned in an unsupervised fashion from arbitrarily orientated training samples. The proposed approach is general enough to be used with a large category of orientation-selective texture features.

PDF CVPR Semantic Scholar

Cite

Text

Newsam and Manjunath. "Normalized Texture Motifs and Their Application to Statistical Object Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.408

Markdown

[Newsam and Manjunath. "Normalized Texture Motifs and Their Application to Statistical Object Modeling." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/newsam2004cvpr-normalized/) doi:10.1109/CVPR.2004.408

BibTeX

@inproceedings{newsam2004cvpr-normalized,
  title     = {{Normalized Texture Motifs and Their Application to Statistical Object Modeling}},
  author    = {Newsam, Shawn D. and Manjunath, B. S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {45},
  doi       = {10.1109/CVPR.2004.408},
  url       = {https://mlanthology.org/cvpr/2004/newsam2004cvpr-normalized/}
}