基于数学形态学的联机手写字符识别去噪方法

	基于数学形态学的联机手写字符识别去噪方法
	孙嫣 ; 刘瀚猛 ; 芮建武 ; 吴健
刊名	计算机科学
	2009
卷号	36 期号:10 页码:237-239+295
关键词	数学形态学联机手写识别噪声消除细化 Mathematical morphology Online handwriting recognition De-noising Thinning
ISSN号	1002-137X
其他题名	de-noising approach for online handwriting character recognition based on mathematical morphology
中文摘要	手写输入时由于笔尖抖动等原因产生了大量噪声,有效地去除噪声是手写识别的前提和关键。根据联机手写识别中手写体字符形态的特性,分析了手写时由于各种原因而产生的噪声,运用数学形态学中膨胀、腐蚀、细化等基本运算,提出了一种将数学形态学应用于联机手写识别预处理的方法,该方法可以有效地消除大量的冗余信息。测试结果表明,提出的方法可行,具有很好的鲁棒性,可以配合其他方案应用于各种联机手写字符识别中。
收录类别	cnki,wanfang,cscd
语种	中文
公开日期	2010-08-24
附注	There are lots of various noises when users are writing characters on the tablet.It's significant to eliminate these noises in order to make these characters be recognized accurately. According to the features of online handwriting characters, we analyzed all sorts of noises generated during writing on the tablet By applying erosion,dilation,thinning operations of the mathematical morphology into pre-processing of online handwriting recognition,a de-noising approach was proposed in this article. Using appropriate structure elements, we can eliminate large amounts of noises in the glyphs of characters. The experiment shows that this solution is valid and robust for online handwriting character recognition.
内容类型	期刊论文
源URL	[http://124.16.136.157/handle/311060/4154]
专题	软件研究所_开放系统与中文信息处理小组_期刊论文
推荐引用方式 GB/T 7714	孙嫣,刘瀚猛,芮建武,等. 基于数学形态学的联机手写字符识别去噪方法[J]. 计算机科学,2009,36(10):237-239+295.
APA	孙嫣,刘瀚猛,芮建武,&吴健.(2009).基于数学形态学的联机手写字符识别去噪方法.计算机科学,36(10),237-239+295.
MLA	孙嫣,et al."基于数学形态学的联机手写字符识别去噪方法".计算机科学 36.10(2009):237-239+295.