ML Anthology

Part Segmentation for Object Recognition

Alex Pentland
NeCo 1989 pp. 82-91
doi:10.1162/NECO.1989.1.1.82 /neco/1989/pentland1989neco-part/

Abstract

Visual object recognition is a difficult problem that has been solved by biological visual systems. An approach to object recognition is described in which the image is segmented into parts using two simple, biologically-plausible mechanisms: a filtering operation to produce a large set of potential object parts, followed by a new type of network that searches among these part hypotheses to produce the simplest, most likely description of the image's part structure.

NeCo Semantic Scholar

Cite

Text

Pentland. "Part Segmentation for Object Recognition." Neural Computation, 1989. doi:10.1162/NECO.1989.1.1.82

Markdown

[Pentland. "Part Segmentation for Object Recognition." Neural Computation, 1989.](https://mlanthology.org/neco/1989/pentland1989neco-part/) doi:10.1162/NECO.1989.1.1.82

BibTeX

@article{pentland1989neco-part,
  title     = {{Part Segmentation for Object Recognition}},
  author    = {Pentland, Alex},
  journal   = {Neural Computation},
  year      = {1989},
  pages     = {82-91},
  doi       = {10.1162/NECO.1989.1.1.82},
  volume    = {1},
  url       = {https://mlanthology.org/neco/1989/pentland1989neco-part/}
}