应用主分量分析与粗糙集处理的特征提取
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
近年来,随着软计算理论的不断发展,粗糙集理论已经成为了目前研究的重点领域。论文讨论了主分量分析(PCA)与粗糙集的理论,并应用于图像特征提取中。采用PCA对输入向量进行甄别,应用粗糙集理论约简与分类无关或关系不大的向量。研究结果表明:在主成分分析中结合粗糙集理论可以排除无关向量的影响,并有效地进行特征提取。试验结果表明了结合两者能够提高模式分类的特征提取的效果。
With the recently developing of soft computing,Rough set theory,however,is being a hot research spot.In this paper,we discuss both Principle Component Analysis(PCA)and rough set theory,and apply them in feature extraction of image classification.We use PCA on selecting the input vector,and use rough set on reducing the inessential factors for classification.Our research indicate that using rough set and PCA together can exclude the unuseful factors and get a minimal set of vectors for image classification.The test results prove the better effects on using both them in pattern recognition than the method which only using PCA or rough set.
引文
1.王碧泉,陈祖荫.模式识别犤M犦.北京:地震出版社,1989:39~51
    2.孙即祥等著.模式识别中的特征提取与计算机视觉不变量犤M犦.北京:国防工业出版社,2001:63~68
    3.DudaRO,HartPE,StorkDG.PatternClassificationandSceneAnalysis犤M犦.2nded,NewYork:JohnWiley&Sons,Inc,1998
    4.曾黄麟.粗糙集理论及其应用(修订版)犤M犦.重庆:重庆大学出版社,1996
    5.PawlakZ.Roughsets:TheoreticalAspectsofReasoningaboutdata犤M犦.Nowowiejska15/19,Warsaw,Poland,1990
    6.PawlakZ.RoughSets犤J犦.IntJComputSci,1982;11:341~356
    7.UCIRepositoryOfMachineLearningDatabasesandDomainTheories.http://www.ics.uci.edu/~mlearn/MLRepository.html,2003-04-16
    8.宋余庆.基于内容理解的医学图像检索关键技术研究.江苏省镇江市社会发展研究项目(SH2002039,SH2003014)

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心