基于核PCA与SVM算法的木材缺陷识别

Application of KPCA and SVM to Wood Defect Recognition

木材缺陷是影响木材产业化推广的重要因素之一,通过合理的木材缺陷识别方法可以有效规避木材缺陷在实际应用中带来的资源浪费问题,同时大幅提高木材的实际利用率。针对木材节子非线性的特征,提出了一种新颖的木材缺陷识别方法。首先,通过核主成分分析方法(Kernel Principal Component Analysis,KPCA),采用多项式的核函数(Polynomial kernel function)对木材原始的非线性数据从低维映射到高维线性特征空间,然后再对映射空间中的线性样本进行降维处理,目的是为了提取到样本的特征参数。其次,结合SVM模型,选择多项式核函数,完成对木材缺陷的识别。最后,通过比较实验所得数据与实测数据,实验结果表明本文提出的方法有较高的识别精度和识别效率。

Wood defect is an important factor affecting thc wood industrialization promotion. A rcasonable wood defect recognition method can effectively avoid the waste of resources caused by wood defects in the practical application. At the same time it can raise the actual utilization of wood. Considering characteristic of wood defects,a new wood defect recognition method is proposed. Firstly,mapping wood original nonlinear data from low dimensional to high dimensional linear feature space using the polynomial kernel function. And then the mapping space of linear dimension reduction processing samples. The purpose is to extract the feature parameters to the samples. Next by means of the SVM model, the polyno-mial kernel function is selected to complete the wood defect identification. The experimental that the proposed method has higher recognition accuracy and efficiency by comparing the data from expe-- iment and the measured data.