Target Classification Based on Fuzzy Clustering Analysis Method

This paper presents a target classification based on fuzzy equivalence relation. Firstly, utilizing improved six invariant moments obtain the objective characteristic matrix. Secondly, a kind of feature weighting function is proposed, making the data classification more effective. Then a fuzzy equivalence relation based on weighted feature matrix can be constructed. Finally, using F statistic to determine the optimal threshold, and completing classification of targets. Experiment results show that it is an efficient clustering algorithm with rapid speed and high precision.