A Self-Organizing Integrated Segmentation and Recognition Neural Net

Abstract

We present a neural network algorithm that simultaneously performs seg(cid:173) mentation and recognition of input patterns that self-organizes to detect input pattern locations and pattern boundaries. We demonstrate this neu(cid:173) ral network architecture on character recognition using the NIST database and report on results herein. The resulting system simultaneously seg(cid:173) ments and recognizes touching or overlapping characters, broken charac(cid:173) ters, and noisy images with high accuracy.

Cite

Text

Keeler and Rumelhart. "A Self-Organizing Integrated Segmentation and Recognition Neural Net." Neural Information Processing Systems, 1991.

Markdown

[Keeler and Rumelhart. "A Self-Organizing Integrated Segmentation and Recognition Neural Net." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/keeler1991neurips-selforganizing/)

BibTeX

@inproceedings{keeler1991neurips-selforganizing,
  title     = {{A Self-Organizing Integrated Segmentation and Recognition Neural Net}},
  author    = {Keeler, Jim and Rumelhart, David E.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {496-503},
  url       = {https://mlanthology.org/neurips/1991/keeler1991neurips-selforganizing/}
}