Comparison of crisp and fuzzy character neural networks in handwritten word recognition
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 3 (3) , 357-363
- https://doi.org/10.1109/91.413223
Abstract
Experiments comparing neural networks trained with crisp and fuzzy desired outputs are described. A handwritten word recognition algorithm using the neural networks for character level confidence assignment was tested on images of words taken from the United States Postal Service mailstream. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level. This empirical result is interpreted as an example of the principle of least commitmentKeywords
This publication has 3 references indexed in Scilit:
- Comparison of crisp and fuzzy character neural networks in handwritten word recognitionIEEE Transactions on Fuzzy Systems, 1995
- Off-line cursive script word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A fuzzy K-nearest neighbor algorithmIEEE Transactions on Systems, Man, and Cybernetics, 1985