CASIA OpenIR  > 09年以前成果
An integration approach to handwritten Chinese character recognition system
Hao, HW; Dai, RW
发表期刊SCIENCE IN CHINA SERIES E-TECHNOLOGICAL SCIENCES
1998-02-01
卷号41期号:1页码:101-105
文章类型Article
摘要A network integration method suitable for Chinese character recognition which combines traditional statistical method and artificial neural network is proposed to deal with the problems in machine recognition of handwritten Chinese characters which have the properties of large vocabulary, complex structure, lots of similar characters and variations of character shape due to handwriting. Four different classifiers for handwritten Chinese character recognition are integrated by the proposed method. The experimental results show that the method has a fast learning speed as well as high accuracy and can greatly improve the system performance.
关键词Handwritten Chinese Character Recognition Artificial Neural Network Integration Network Integration
WOS标题词Science & Technology ; Technology
收录类别SCI
语种英语
WOS研究方向Engineering ; Materials Science
WOS类目Engineering, Multidisciplinary ; Materials Science, Multidisciplinary
WOS记录号WOS:000071615000015
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/9767
专题09年以前成果
作者单位Chinese Acad Sci, Inst Automat, AI Lab, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Hao, HW,Dai, RW. An integration approach to handwritten Chinese character recognition system[J]. SCIENCE IN CHINA SERIES E-TECHNOLOGICAL SCIENCES,1998,41(1):101-105.
APA Hao, HW,&Dai, RW.(1998).An integration approach to handwritten Chinese character recognition system.SCIENCE IN CHINA SERIES E-TECHNOLOGICAL SCIENCES,41(1),101-105.
MLA Hao, HW,et al."An integration approach to handwritten Chinese character recognition system".SCIENCE IN CHINA SERIES E-TECHNOLOGICAL SCIENCES 41.1(1998):101-105.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Hao, HW]的文章
[Dai, RW]的文章
百度学术
百度学术中相似的文章
[Hao, HW]的文章
[Dai, RW]的文章
必应学术
必应学术中相似的文章
[Hao, HW]的文章
[Dai, RW]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。