QQ客服 官方微博 反馈留言

	Cascade MQDF classifier for handwritten character recognition
	Fu Qiang ; Ding Xiaoqing ; Liu Changsong
	2010-10-12 ; 2010-10-12
关键词	Theoretical or Mathematical/ Gaussian processes handwriting recognition handwritten character recognition maximum likelihood estimation/ cascade MQDF classifier unconstrained handwritten character recognition cascade structure-based ensemble method generalized recognition confidence multilayer Gaussian models maximum likelihood model HCL2000 THOCR-HCD handwritten Chinese character recognition databases/ C1250B Character recognition C1140Z Other topics in statistics
中文摘要	The accuracy of unconstrained handwritten character recognition is improved by a cascade MQDF classifier. The cascade structure-based ensemble method combines recognition results at the measurement level. The generalized recognition confidence is used as the measurement of recognition result. The algorithm uses multilayer Gaussian models to elaborately descript the sample distributions to improve the recognition rate. The paper then uses the maximum likelihood model to interpret the ensemble algorithm mechanism. The algorithm was applied to the HCL2000 and THOCR-HCD handwritten Chinese character recognition databases and achieved 10.75%, 9.82% and 25.31% error reductions.
语种	中文
出版者	Tsinghua University Press ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/82377]
专题	清华大学
推荐引用方式 GB/T 7714	Fu Qiang,Ding Xiaoqing,Liu Changsong. Cascade MQDF classifier for handwritten character recognition[J],2010, 2010.
APA	Fu Qiang,Ding Xiaoqing,&Liu Changsong.(2010).Cascade MQDF classifier for handwritten character recognition..
MLA	Fu Qiang,et al."Cascade MQDF classifier for handwritten character recognition".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。