Show simple item record

dc.contributor.advisor谭忠
dc.contributor.advisor王焰金
dc.contributor.author刘晓红
dc.date.accessioned2018-12-05T01:40:20Z
dc.date.available2018-12-05T01:40:20Z
dc.date.issued2017-12-27
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/170032
dc.description.abstract字母识别是字符识别的一个特例,正确识别字符信息并实现自动录入在信息化建设快速发展的今天拥有越来越重要的意义。在过去几十年中,很多学者将多种分类算法应用于字母识别领域,包括贝叶斯分类器、BP神经网络、支持向量机等。其中,支持向量机(SVM)分类算法因其趋于完善的理论研究和算法实现研究,及克服维灾难和过拟合的优点,在字符识别领域取得了理想的效果。但支持向量机的算法复杂度受到样本规模的直接影响,且对噪声和孤立点较为敏感。因此,如何有效挑选经典样本成为提高模型分类性能的关键。 考虑到AP聚类算法具有如下两个优点:其一,算法无须事先指定聚类个数;其二,算法具有很低的均方误差,因此可借助AP聚类算法...
dc.description.abstractLetter recognition is a special case of character recognition. The correct recognition of character information and achieve automatic entry have more and more important significance in the rapid development of information technology today. In the past few decades, many scholars have applied a variety of classification algorithms to letter recognition, including Bayesian classifier, BP neural netwo...
dc.language.isozh_CN
dc.relation.urihttps://catalog.xmu.edu.cn/opac/openlink.php?strText=58274&doctype=ALL&strSearchType=callno
dc.source.urihttps://etd.xmu.edu.cn/detail.asp?serial=60800
dc.subject字母识别
dc.subject支持向量机
dc.subjectAP聚类
dc.subject改进的AP-SVM
dc.subjectLetter recognition
dc.subjectSVM
dc.subjectAP clustering
dc.subjectImproved AP-SVM
dc.title改进的AP-SVM算法研究及其在字母识别的应用
dc.title.alternativeResearch on Improved AP - SVM Algorithm and Its Application in Letter Recognition
dc.typethesis
dc.date.replied2017-05-26
dc.description.note学位:理学硕士
dc.description.note院系专业:数学科学学院_应用数学
dc.description.note学号:19020141152630


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record