Self-organizing integrated segmentation and recognition neural network

James D. Keeler; David E. Rumelhart

doi:10.1117/12.140155

Translator Disclaimer

1 July 1992 Self-organizing integrated segmentation and recognition neural network

James D. Keeler, David E. Rumelhart

Author Affiliations +

Proceedings Volume 1710, Science of Artificial Neural Networks; (1992) https://doi.org/10.1117/12.140155
Event: Aerospace Sensing, 1992, Orlando, FL, United States

Abstract

We present a neural network algorithm that simultaneously performs segmentation and recognition of input patterns that self-organizes to detect input pattern locations and pattern boundaries. We outline the algorithm and demonstrate this neural network architecture and algorithm on character recognition using the NIST database and report results herein. The resulting system simultaneously segments and recognizes touching characters, overlapping characters, broken characters, and noisy images with high accuracy. We also detail some of the characteristics of the algorithm on an artificial database in the appendix.

Citation Download Citation

James D. Keeler and David E. Rumelhart "Self-organizing integrated segmentation and recognition neural network", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); https://doi.org/10.1117/12.140155

ACCESS THE FULL ARTICLE