首页 | 本学科首页   官方微博 | 高级检索  
     

结合Fisher判别的手写数字特征提取方法
引用本文:周慧灿,刘琼,王耀南.结合Fisher判别的手写数字特征提取方法[J].计算机工程与设计,2007,28(8):1870-1872.
作者姓名:周慧灿  刘琼  王耀南
作者单位:1. 湖南文理学院,计算机科学系,湖南,常德,415000
2. 湖南大学,电气与信息工程学院,湖南,长沙,410082
基金项目:高等学校博士学科点专项科研项目
摘    要:在手写数字图像的特征提取中,提出一种结合Fisher线性判别的多分辨率Gabor滤波方法,在所有特征点上寻求特定滤波方向上的局部最优滤波频率,以获得最佳滤波效果,同时压缩不相关特征.在MNIST手写数字图像库上的识别实验表明:在小样本情况下,该方法能更准确地抽取手写数字图像特征,识别效果明显优于直接进行Gabor特征提取.

关 键 词:多分辨率Gabor滤波  Fisher线性判别  手写数字识别  特征提取  LIBSVM  结合  Fisher  线性判别  手写数字  特征提取  滤波方法  features  Method  识别效果  图像特征  抽取  情况  小样本  实验  图像库  不相关特征  压缩  滤波效果  最佳  滤波频率
文章编号:1000-7024(2007)08-1870-03
修稿时间:2006-05-16

Method for extracting features of handwritten numeral combining fisher's discriminant
ZHOU Hui-can,LIU Qiong,WANG Yao-nan.Method for extracting features of handwritten numeral combining fisher''''s discriminant[J].Computer Engineering and Design,2007,28(8):1870-1872.
Authors:ZHOU Hui-can  LIU Qiong  WANG Yao-nan
Affiliation:1. Department of Computer Science, Hunan University of Art and Science, Changde 415003, China; 2. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
Abstract:In extracting the features of handwritten numeral,a method bases on multi-resolution Gabor filter which combined Fisher's linear discriminant is presented.According to the method,local optimum filtering frequencies in certain orientations is determined at all of the feature points.The purpose is to obtain the best filtering results and compress the irrelevant features.Experiments for handwritten numeral recognition to MNIST database indicates that the method can extract the features of handwritten numeral more efficiently and the effect of recognition is obviously better than directly extracting Gabor features conditions of small sample.
Keywords:multi-resolution Gabor filter  fisher's linear discriminant  handwritten numeral recognition  features extracting  LIBSVM
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