Abstract
In this paper, we describe a neural-network-based handwritten alphabetic character recognition system. Feature vectors are generated using a two-pass algorithm to generate direction magnitude images followed by summing over overlapping zones. Crisp neural networks and fuzzy neural networks are trained using back-propagation. In the crisp case, the desired output is high for the correct class and low for all others. In the fuzzy case, the desired outputs are set using a fuzzy k-nearest neighbor algorithm.
Original language | English |
---|---|
Pages | 421-426 |
Number of pages | 6 |
Publication status | Published - 1992 |
Event | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA Duration: 1992 Nov 15 → 1992 Nov 18 |
Other
Other | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 |
---|---|
City | St.Louis, MO, USA |
Period | 92-11-15 → 92-11-18 |
All Science Journal Classification (ASJC) codes
- Software