主观引导特征提取法在光谱识别中的应用  

Application of Subjective Introduction Feature Extraction Mothod in Spectrum Discrimination

作　　者：陈伟 瞿晓[2] 葛丁飞[3] 

机构地区：[1]浙江省科技咨询中心,杭州310003 [2]浙江科技学院电气工程学院,杭州310043 [3]浙江科技学院信息学院,杭州310043

出　　处：《科技通报》2011年第4期591-594,共4页Bulletin of Science and Technology

摘　　要：在许多情况下,并非所有类别都有着同样的重要性和实际意义,我们希望在特征提取时能体现出类间重要性和意义上的差异,而传统特征提取方法缺乏解决这一问题的能力。为此,利用一种基于主观引导特征提取法对光谱数据进行特征提取和分类,其主要思想是:将人的主观意图融合到特征提取中,提取有利于具有优先权类别的分类特征。结果表明,与传统线性鉴别分析法(LDA)相比较,该方法可获得更加有效的分类特征.In most cases, it is more important and significant to recognize certain specific classes rather than to discriminate all the classes. It is desired that the differences on the imporrtance and significance can be reflected during the feature extraction. The subjective introduction based method was used and applied to the feature extraction of spectrum, which the subjective significance was introduced into the feature extraction for the classification with priority. The experimental results show that the proposed feature extraction method can obtain more effective features compared to conventional linear discriminant analysis （LDA） methods.

关 键 词：光谱 特征提取 可分性 分类 

分 类 号：TH744.1[机械工程—光学工程]