提出了一种基于聚类选择的分类器集成方法,通过聚类把模式特征空间划分成不相交的区域,对于初始分类器集合,各区域给出分类器的删除分值,各分类器总分值确定其删除优先级别,由删除优先级别选择一组分类器组成集成。理论分析和实验结果表明,基于聚类选择的分类器集成方法能够更好地对模式进行分类。
The feature space was partitioned into disjoined regions, which gave the dismission scores of classifiers in the ensemble. Total score decided by all regions orders the preferential rank for classifiers dismission, by which a set of classifiers was selected from original classifiers. Theoretic analysis and experiment results show that the classifiers ensemble method is efficient for pattern recognition.