文件名称:WCECS2008pp207209
介绍说明--下载内容来自于网络,使用问题请自行百度
This paper proposed a new method for recognizing
machine printed Arabic characters. First, four edges (left, upper,
lower, and right edge) are extracted from the character image.
Next, some features are extracted from the edges. Finally, a
BPNN, isolated forms of Arabic characters are recognized. The
new method is tested on two fonts and 9 sizes, and its
recognition rate is over 97
machine printed Arabic characters. First, four edges (left, upper,
lower, and right edge) are extracted from the character image.
Next, some features are extracted from the edges. Finally, a
BPNN, isolated forms of Arabic characters are recognized. The
new method is tested on two fonts and 9 sizes, and its
recognition rate is over 97
(系统自动生成,下载前可以参看下载内容)
下载文件列表
WCECS2008_pp207-209[1].pdf
本网站为编程资源及源代码搜集、介绍的搜索网站,版权归原作者所有! 粤ICP备11031372号
1999-2046 搜珍网 All Rights Reserved.