Parallel compact integration in handwritten Chinese character recognition
Wang, CH; Xiao, BH; Dai, RW
2004-02-01
发表期刊SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES
卷号47期号:1页码:89-96
文章类型Article
摘要In this paper, a new parallel compact integration scheme based on multi-layer perceptron (MLP) networks is proposed to solve handwritten Chinese character recognition (HCCR) problems. The idea of metasynthesis is applied to HCCR, and compact MLP network classifier is defined. Human intelligence and computer capabilities are combined together effectively through a procedure of two-step supervised learning. Compared with previous integration schemes, this scheme is characterized with parallel compact structure and better performance. It provides a promising way for applying MLP to large vocabulary classification.
关键词Handwritten Chinese Character Recognition (Hccr) Metasynthesis Multi-layer Perceptron (Mlp) Compact Mlp Network Classifier Supervised Learning
WOS标题词Science & Technology ; Technology
关键词[WOS]CLASSIFIERS
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems
WOS记录号WOS:000188951100008
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/7968
专题复杂系统管理与控制国家重点实验室_影像分析与机器视觉
作者单位Chinese Acad Sci, Inst Automat, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Wang, CH,Xiao, BH,Dai, RW. Parallel compact integration in handwritten Chinese character recognition[J]. SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES,2004,47(1):89-96.
APA Wang, CH,Xiao, BH,&Dai, RW.(2004).Parallel compact integration in handwritten Chinese character recognition.SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES,47(1),89-96.
MLA Wang, CH,et al."Parallel compact integration in handwritten Chinese character recognition".SCIENCE IN CHINA SERIES F-INFORMATION SCIENCES 47.1(2004):89-96.
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
[Wang, CH]的文章
[Xiao, BH]的文章
[Dai, RW]的文章
百度学术
百度学术中相似的文章
[Wang, CH]的文章
[Xiao, BH]的文章
[Dai, RW]的文章
必应学术
必应学术中相似的文章
[Wang, CH]的文章
[Xiao, BH]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。