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 |
|---|---|
| Title of host publication | Intelligent Engineering Systems Through Artificial Neural Networks |
| Editors | C.H. Dagli, L.I. Burke, Y.C. Shin |
| Publisher | ASME |
| Pages | 421-426 |
| Number of pages | 6 |
| Volume | 2 |
| 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 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
Cite this
}
Fuzzy and crisp handwritten character recognition using neural networks. / Gader, Paul; Mohamed, Magdi; Chiang, Jung-Hsien.
Intelligent Engineering Systems Through Artificial Neural Networks. ed. / C.H. Dagli; L.I. Burke; Y.C. Shin. Vol. 2 ASME, 1992. p. 421-426.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Fuzzy and crisp handwritten character recognition using neural networks
AU - Gader, Paul
AU - Mohamed, Magdi
AU - Chiang, Jung-Hsien
PY - 1992
Y1 - 1992
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=0027105377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027105377&partnerID=8YFLogxK
M3 - Conference contribution
VL - 2
SP - 421
EP - 426
BT - Intelligent Engineering Systems Through Artificial Neural Networks
A2 - Dagli, C.H.
A2 - Burke, L.I.
A2 - Shin, Y.C.
PB - ASME
ER -