Abstract: A classifiers ensemble approach based on Principal Component Analysis (PCA) was proposed. Lots of original classifiers were got from Random Subspace Method (RSM). According to their classification performance, their preservation scores were given, so the preferential ranks for classifiers preservation were ordered, by which a set of classifiers was selected from original classifiers. Theoretic analysis and experimental results in face database ORL show that this pattern classification method based on ensemble PCA is efficient for pattern recognition.

Key words: face recognition, dimension reduction, principal component analysis, classifiers ensemble

摘要： 设计了一种基于主成分分析的分类器集成方法。应用随机子空间法获得多个初始分类器，由它们的分类性能给出分类器的保留分值，从而确定它们的保留优先级别，最后由保留优先级别选择一组分类器组成集成。理论分析和在人脸数据库ORL上的实验结果表明，这种基于集成PCA的分类方法能够更好地对模式进行分类。

关键词: 人脸识别, 维数约简, 主成份分析, 分类器集成