Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)
- 1998.06a
- /
- Pages.707-712
- /
- 1998
Handwritten Digit Recognition with Softcomputing Techniques
Abstract
This paper presents several softcomputing techniques such as neural networks, fuzzy logic and genetic algorithms : Neural networks as brain metaphor provide fundamental structure, fuzzy logic gives a possibility to utilize top-down knowledge from designer, and genetic algorithms as evolution metaphor determine several system parameters with the process of bottom up development. With these techniques, we develop a pattern recognizer which consists of multiple neural networks aggregated by fuzzy integral in which genetic algorithms determine the fuzzy density values. The experimental results with the problem of recognizing totally unconstrained handwritten numeral show that the performance of the proposed method is superior to that of conventional methods.
Keywords