Paper sheet defects classification based on support vector machine method
基于支持向量机的纸张缺陷图像分类识别

We proposed a paper sheet defects classification method based on SVM according to its good performance in small data sets and high dimension feature spaces. To classify three common defects of the paper sheet, we firstly preprocessed the defect images, then carefully selected the input features for training the SVM-based classifiers, and optimized the parameters and the classifiers by the cross-validation method. The results prove that SVM is practical in paper sheet defects classification and identification.