Optimal pattern recognition is a hard problem in data classification experimentations. Highly performing models with low computational complexity are ideal in real-time environment. In this paper, a soft computing approach is proposed for this aim. In particular, the Fuzzy formulation of Shannon Entropy is used to obtain mathematical and experimental models of a Fuzzy machine for pattern recognition, with optimal inference capabilities and minimal entropy values. The proposed approach has been evaluated in Synthetic Aperture Radar imagery, in comparison with the classical Shannon's Fuzzy Entropy and a Support Vector Machine Classifier.
|Titolo:||“Fuzzy Classification with Minimal Entropy Models to Solve Pattern Recognition Problems: a Compared Evaluation in SAR Imagery”|
|Data di pubblicazione:||2006|
|Appare nelle tipologie:||1.1 Articolo in rivista|