ML Anthology

Recognition of Geons by Parametric Deformable Contour Models

Maurizio Pilu, Robert B. Fisher
ECCV 1996 pp. 71-82
doi:10.1007/BFB0015524 /eccv/1996/pilu1996eccv-recognition/

Abstract

This paper presents a novel approach to the detection and recognition of qualitative parts like geons from real 2D intensity images. Previous works relied on semi-local properties of either line drawings or good region segmentation. Here, in the framework of Model-Based Optimisation, whole geons or substantial sub-parts are recognised by fitting parametric deformable contour models to the edge image by means of a Maximum A Posteriori estimation performed by Adaptive Simulated Annealing, accounting for image clutter and limited occlusions. A number of experiments, carried out both on synthetic and real edge images, are presented.

PDF ECCV Semantic Scholar

Cite

Text

Pilu and Fisher. "Recognition of Geons by Parametric Deformable Contour Models." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015524

Markdown

[Pilu and Fisher. "Recognition of Geons by Parametric Deformable Contour Models." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/pilu1996eccv-recognition/) doi:10.1007/BFB0015524

BibTeX

@inproceedings{pilu1996eccv-recognition,
  title     = {{Recognition of Geons by Parametric Deformable Contour Models}},
  author    = {Pilu, Maurizio and Fisher, Robert B.},
  booktitle = {European Conference on Computer Vision},
  year      = {1996},
  pages     = {71-82},
  doi       = {10.1007/BFB0015524},
  url       = {https://mlanthology.org/eccv/1996/pilu1996eccv-recognition/}
}