Character recognition: Qualitative reasoning and neural networks

Ervin Y. Rodin, Yuanlan Wu, S. Massoud Amin

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Traditional character recognition methods construct a grid and represent a character as a combination of grid dots. By using a qualitative representation method [1,2], we introduce here a new approach to representing English letters. Using properties of the qualitative representation method, we can uniquely represent each English letter regardless of the size and position of each stroke on the board. Our success of implementation by neural networks shows the feasibility of the method, and our tolerance tests show its robustness.

Original languageEnglish (US)
Pages (from-to)95-104
Number of pages10
JournalMathematical and Computer Modelling
Issue number2
StatePublished - Feb 1992
Externally publishedYes

Bibliographical note

Funding Information:
*This research was supported by AFOSR under Grant No. 890158.


Dive into the research topics of 'Character recognition: Qualitative reasoning and neural networks'. Together they form a unique fingerprint.

Cite this