Multiple Shape-from-Texture into Texture Analysis and Surface Segmentation

Abstract

This paper describes an approach to the classification and segmentation of textured imagery. The approach utilizes information derived during the recovery of surface shape parameters, which are generated by a system that integrates multiple shape-from cues. The robustness of this approach is illustrated by a system that integrates several shape-from-texture cues, recovering not only shape information but also segmenting images into surfaces and aiding in the classification of the surface textures. Two examples are given of the system operating on real, camera acquired imagery.

Cite

Text

Moerdler. "Multiple Shape-from-Texture into Texture Analysis and Surface Segmentation." IEEE/CVF International Conference on Computer Vision, 1988. doi:10.1109/CCV.1988.590007

Markdown

[Moerdler. "Multiple Shape-from-Texture into Texture Analysis and Surface Segmentation." IEEE/CVF International Conference on Computer Vision, 1988.](https://mlanthology.org/iccv/1988/moerdler1988iccv-multiple/) doi:10.1109/CCV.1988.590007

BibTeX

@inproceedings{moerdler1988iccv-multiple,
  title     = {{Multiple Shape-from-Texture into Texture Analysis and Surface Segmentation}},
  author    = {Moerdler, Mark L.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1988},
  pages     = {316-320},
  doi       = {10.1109/CCV.1988.590007},
  url       = {https://mlanthology.org/iccv/1988/moerdler1988iccv-multiple/}
}