基于SVD和SVM的复杂背景噪声图像的纸病辨识  

Recognition of Paper Defect Image with Complex Background Noise Based on SVD and SVM

作　　者：周强[1] 齐璐[1] 张慧[1] 

机构地区：[1]陕西科技大学电气与信息工程学院,陕西西安710021

出　　处：《中国造纸学报》2016年第2期49-54,共6页Transactions of China Pulp and Paper

基　　金：陕西省科技统筹创新工程计划项目(2012KTCQ01-19);陕西省科技攻关项目(2011K06-06);西安市未央区科技计划项目201304

摘　　要：针对纸病图像的复杂背景噪声造成的纸病辨识结果不理想的问题,提出一种基于奇异值分解(SVD)和支持向量机(SVM)的纸病辨识方法:首先利用多层二维小波对纸病图像背景噪声去噪,然后用SVD对纸病进行特征提取,最后采用SVM对纸病进行辨识。实验结果表明,该方法可以有效辨识纸病,且不受实际生产过程中图像复杂背景噪声的影响。In order to conduct defect identification satisfactorily from the paper defect image with complex background noise,a paper defect identification method based on singular value decomposition（ SVD） technique and support vector machine（ SVM） was proposed,i. e multidimensional wavelet was used to remove background noise,SVD was employed to extract paper defect characteristics and SVM was used to recognize paper defect. The experimental results showed that the method could recognize paper defects effectively without influencing by the complex background noise in practical production process.

关 键 词：奇异值分解技术 纸病图像 图像背景噪声 二维小波变换 支持向量机 

分 类 号：TS77[轻工技术与工程—制浆造纸工程]