一种自适应最大拒绝鉴别分析及其鉴别矢量集  

Adaptive Maximal Rejection Discriminant Analysis and Its Discriminant Vectors

作　　者：郭志波[1,2] 严云洋[3] 杨静宇[2] 赵春霞[2] 

机构地区：[1]扬州大学信息工程学院,扬州225009 [2]南京理工大学计算机科学与技术学院,南京210094 [3]淮阴工学院计算机科学与技术学院,淮阴223003

出　　处：《模式识别与人工智能》2010年第4期501-507,共7页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金重点项目(No.60632050);国家自然科学基金项目(No.60875004);江苏省高校自然科学基础研究计划项目(No.08KJB510023)资助

摘　　要：针对MRC-Boosting方法中的弱分类器二值化以及鉴别矢量不正交等问题,提出一种自适应最大拒绝鉴别分析(AdaMRDA),进一步提高分类性能.通过已抽取的鉴别特征到期望中心的距离,设计一种自适应权重调整方法,使得后面得到的鉴别矢量更加有利于分类,并且给出最佳正交鉴别矢量集的求解方程.最后,通过在2个数据库上的实验证明,AdaMRDA方法在分类性能上明显优于MRC-Boosting方法及相关方法.Aiming at the two-value output of weak classifiers and Non-orthogonal discriminant vectors on the MRC-Boosting, an adaptive maximal rejection discriminant analysis （AdaMRDA） is proposed to further improve the classification performance. Based on the Euclid distance between the extracted discriminant features and their expectation mean, an adaptive updating weights method is developed firstly, by which the latter discriminant vectors obtained are more beneficial for classification. Then the equation solving the optimal orthogonal discriminant vectors is given. Finally, the experimental results on 2 databases prove that AdaMRDA is superior to MRC-Boosting and related methods on classification performance.

关 键 词：特征抽取 最大拒绝分类器(MRC) 线性鉴别分析(LDA) BOOSTING 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]