This paper introduces backpropagation neural network as a classifier with some practical considerations, and proposes a two-stage classification scheme based on this classifier. A preliminary experiment with a large set of Hangul (Korean script) confirms the superiority relative to a single large neural network classifier.
Bibliographical noteFunding Information:
This work w~,~ supported in part by a grant from the Korea Science and Engineering Foundation (KOSEF) and a grant from the Korea Advanced Institute of Science and Technology.
All Science Journal Classification (ASJC) codes
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence