主元分析法在木材缺陷轮廓特征提取中的应用研究  

Application of Principal Component Analysis Method Wood Defect Contour Feature Extraction

作　　者：李丽[1] 万年红[2] 白陈祥 张金玉[1] 吕晓依[1] 

机构地区：[1]中国林业科学研究院,北京100091 [2]黎明职业大学,福建泉州362000 [3]北京华创维想科技开发有限责任公司,北京100071

出　　处：《林业机械与木工设备》2010年第11期19-21,23,共4页Forestry Machinery & Woodworking Equipment

摘　　要：针对木材缺陷中圆形节、大虫眼轮廓特征的特点,提出一种基于主元分析的非线性轮廓特征提取方法。采用主元贡献率法选定木材缺陷轮廓特征的主元个数,建立主分量方程,计算木材缺陷轮廓特征值样本的主分量值,从而构建出新的木材缺陷轮廓特征向量综合指标,为木材缺陷模式识别系统的建立和学习提供输入向量。In viewof the characteristics of the contour features of such wood defects as circular knots and large insect holes,a nonlinear contour feature extraction method based on the principal component analysis method（PCA） is presented.The number of principal components of wood defect contour features is determined with the primary component contribution rate method and a principal component equation is established to calculate the main component value of the samples of wood defect contour feature values,therefore establishing a new composite index of wood defect contour feature vectors to provide input vectors for the establishment and study of a wood defect mode identification system.

关 键 词：主元分析 缺陷检测 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]