首页 | 本学科首页   官方微博 | 高级检索  
     

MNIST邮政编码手写数字识别的研究
引用本文:崔海霞,杨红,刘佐濂. MNIST邮政编码手写数字识别的研究[J]. 广州大学学报(自然科学版), 2009, 8(4)
作者姓名:崔海霞  杨红  刘佐濂
作者单位:广州大学,物理与电子工程学院,广东,广州,510006;华南理工大学,电信学院,广东,广州,510640;广州大学,物理与电子工程学院,广东,广州,510006
摘    要:手写数字识别在很多领域都有着广泛的应用前景,论文研究了Gabor滤波器的特性及其特征提取的方法,PCM特征向量选择降低数据维数,SVM支持向量机的原理以及影响其性能的参数,并且克服了传统的维数灾难与过学习现象,用MNIST数据库做了仿真实验,交叉验证取得合适的SVM参数.实验表明,该方法取得了比较理想的结果,验证了SVM的多类分类方法,并与传统的一些分类方法做了比较分析.

关 键 词:MNIST  手写数字识别  Gabor滤波器  支持向量机

Research of zip codes' handwritten digit recognition with MNIST
CUI Hai-xia,YANG Hong,LIU Zuo-lian. Research of zip codes' handwritten digit recognition with MNIST[J]. Journal og Guangzhou University:Natural Science Edition, 2009, 8(4)
Authors:CUI Hai-xia  YANG Hong  LIU Zuo-lian
Affiliation:1.School of Physics and Electronic Engineering;Guangzhou University;Guangzhou 510006;China;2.School of Electronics and Information;South China University of Technology;Guangzhou 510640;China
Abstract:Handwritten digit recognition has wide application foreground in many domains.This paper studied the character of Gabor filter,the methods of feature extractor,principal component analysis,the theory of SVM and its parameters.The method proposed overcame dimension disaster and overfitting.The experiment with MNIST database validated there were ideal results with our method,and also the multi-class SVM was efficient.At last,we analyzed and compared the methods with traditional multi-class classification.
Keywords:MNIST  handwritten digit recognition  Gabor filter  SVM  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号