Knowledge Integration in Text Recognition
Abstract
The paper describes an algorithm based on AI techniques for recognizing words of printed or hand-written text--with the technique developed also applicable to cor-recting substitution spelling errors. The algorithm effectively integrates bottom-up information in the form of letter shapes, letter transitional probabilities and letter classification-error probabilities together with top-down knowledge in the form of a lexicon of legal words repre-sented as a letter trie. Experimental re-sults with the algorithm are reported for the combined top-down and bottom-up ap-proach and for each of the two approaches individually. I
Cite
Text
Srihari and Hull. "Knowledge Integration in Text Recognition." AAAI Conference on Artificial Intelligence, 1982.Markdown
[Srihari and Hull. "Knowledge Integration in Text Recognition." AAAI Conference on Artificial Intelligence, 1982.](https://mlanthology.org/aaai/1982/srihari1982aaai-knowledge/)BibTeX
@inproceedings{srihari1982aaai-knowledge,
title = {{Knowledge Integration in Text Recognition}},
author = {Srihari, Sargur N. and Hull, Jonathan J.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {1982},
pages = {148-151},
url = {https://mlanthology.org/aaai/1982/srihari1982aaai-knowledge/}
}