【作者】 朱晓霞； 孙同景； 陈桂友；

【Author】 ZHU Xiao-xia SUN Tong-jing CHEN Gui-you(Control Science and Engineering,Shandong University,Jinan 250061,China)

【机构】 山东大学控制科学与工程学院；

【摘要】 支持向量机(简称SVM)是建立在统计学习理论基础之上具有严密数学描述的机器学习算法.本文利用SVM解决二类分类问题的优势,设计了一个两级指纹分类器,提出并实现了一种新型的指纹分类的算法.实验表明,分类器具有很好的范化能力,对于新样本分类的正确率达98.5%,算法具有一定实用价值.更多还原

【Abstract】 Support Vector Machine (SVM),which is based on the Statistical Learning Theory,is a Machine Learning algorithm with strict math description.Using the superiority of SVM to solve two-class classification problems,we designed a two-stage fingerprint classifier,presented and realized a novel method about finger- print classification.From the experiment,we can conclude that the classifier has perfect generalization ability and the accuracy for the new sample is 98.5 %,which has value to a certainty in practice.更多还原