The Teachable Letter Recognizer
Abstract
The Teachable Letter Recognizer (TLR) is a program for letter learning which uses a method not vet described in the character recognition literature. TLR has two main characteristics: (1) It uses a discrimination tree as a knowledge representation. The discrimination tree is a quadtree with some additions. (2) The two types of global features that are used to characterise a letter are the density of pixels and the overall color, white, black or grey. TLR is invariant to shifts and shows several interesting effects which are related to human behavior, for example occasionally it becomes confused when learning new letters. TLR's importance as a letter recognition program lies in its ability to recognize some distortions of letters which it has never seen before, and for which it also does not have a transformation algorithm.
Cite
Text
Geller. "The Teachable Letter Recognizer." International Joint Conference on Artificial Intelligence, 1985.Markdown
[Geller. "The Teachable Letter Recognizer." International Joint Conference on Artificial Intelligence, 1985.](https://mlanthology.org/ijcai/1985/geller1985ijcai-teachable/)BibTeX
@inproceedings{geller1985ijcai-teachable,
title = {{The Teachable Letter Recognizer}},
author = {Geller, James},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1985},
pages = {249-251},
url = {https://mlanthology.org/ijcai/1985/geller1985ijcai-teachable/}
}