ML Anthology

Using a Neural Net to Instantiate a Deformable Model

Christopher K. I. Williams, Michael Revow, Geoffrey E. Hinton
NeurIPS 1994 pp. 965-972
/neurips/1994/williams1994neurips-using/

Abstract

Deformable models are an attractive approach to recognizing non(cid:173) rigid objects which have considerable within class variability. How(cid:173) ever, there are severe search problems associated with fitting the models to data. We show that by using neural networks to provide better starting points, the search time can be significantly reduced. The method is demonstrated on a character recognition task.

PDF NeurIPS Semantic Scholar

Cite

Text

Williams et al. "Using a Neural Net to Instantiate a Deformable Model." Neural Information Processing Systems, 1994.

Markdown

[Williams et al. "Using a Neural Net to Instantiate a Deformable Model." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/williams1994neurips-using/)

BibTeX

@inproceedings{williams1994neurips-using,
  title     = {{Using a Neural Net to Instantiate a Deformable Model}},
  author    = {Williams, Christopher K. I. and Revow, Michael and Hinton, Geoffrey E.},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {965-972},
  url       = {https://mlanthology.org/neurips/1994/williams1994neurips-using/}
}