文件名称:Neural-network-recognition-system
- 所属分类:
- 图形/文字识别
- 资源属性:
- [Windows] [Visual C] [源码]
- 上传时间:
- 2012-11-26
- 文件大小:
- 63kb
- 下载次数:
- 0次
- 提 供 者:
- 李**
- 相关连接:
- 无
- 下载说明:
- 别用迅雷下载,失败请重下,重下不扣分!
介绍说明--下载内容均来自于网络,请自行研究使用
使用说明
第一步:训练网络。使用训练样本进行训练。
第二步:识别。首先,打开图像(256色);再次,进行归一化处理,点击“一次性处理”;最后,点击“R”或者使用菜单找到相应项来进行识别。识别的结果显示在屏幕上,同时也输出到文件result.txt中。
该系统的识别率一般情况下为90 。
此外,也可以单独对打开的图片一步一步进行图像预处理工作,但要注意,每一步工作只能执行一遍,而且要按顺序执行。
具体步骤为:“256色位图转为灰度图”-“灰度图二值化”-“去噪”-“倾斜校正”-“分割”-“标准化尺寸”-“紧缩重排”。
注意,待识别的图片要与win.dat和whi.dat位于同一目录,这两文件保存训练后网络的权值参数。-Help
The first step: Training Network. The use of training samples for training.
Step two: identification. First, open the image (256 colors) again, normalized to deal with, click on the "one-time deal" Finally, click "R" or use the menu to find the corresponding items to be identified. Recognition results show up on the screen, but also output to a file Result.txt Medium.
The system s recognition rate under normal circumstances was 90 .
Alternatively, you could open a separate picture of the image pre-processing step by step job, but bearing in mind that each step can only run job again, but according to the order of implementation.
Concrete steps as: "256-color bitmap to grayscale"- "two grayscale values of"- "De-noising"- "tip-tilt correction"- "split"- "the standardization of size"- "tight rearrangement."
Note that to be identified with the picture win.dat and whi.dat located in the same directory, these two files after training the weights of the netw
第一步:训练网络。使用训练样本进行训练。
第二步:识别。首先,打开图像(256色);再次,进行归一化处理,点击“一次性处理”;最后,点击“R”或者使用菜单找到相应项来进行识别。识别的结果显示在屏幕上,同时也输出到文件result.txt中。
该系统的识别率一般情况下为90 。
此外,也可以单独对打开的图片一步一步进行图像预处理工作,但要注意,每一步工作只能执行一遍,而且要按顺序执行。
具体步骤为:“256色位图转为灰度图”-“灰度图二值化”-“去噪”-“倾斜校正”-“分割”-“标准化尺寸”-“紧缩重排”。
注意,待识别的图片要与win.dat和whi.dat位于同一目录,这两文件保存训练后网络的权值参数。-Help
The first step: Training Network. The use of training samples for training.
Step two: identification. First, open the image (256 colors) again, normalized to deal with, click on the "one-time deal" Finally, click "R" or use the menu to find the corresponding items to be identified. Recognition results show up on the screen, but also output to a file Result.txt Medium.
The system s recognition rate under normal circumstances was 90 .
Alternatively, you could open a separate picture of the image pre-processing step by step job, but bearing in mind that each step can only run job again, but according to the order of implementation.
Concrete steps as: "256-color bitmap to grayscale"- "two grayscale values of"- "De-noising"- "tip-tilt correction"- "split"- "the standardization of size"- "tight rearrangement."
Note that to be identified with the picture win.dat and whi.dat located in the same directory, these two files after training the weights of the netw
(系统自动生成,下载前可以参看下载内容)
下载文件列表
神经网络数字识别系统vc++源代码
..............................\Bp.h
..............................\ChildView.cpp
..............................\ChildView.h
..............................\DBpParamater.cpp
..............................\DBpParamater.h
..............................\DIBAPI.CPP
..............................\DIBAPI.H
..............................\DigitRec.aps
..............................\DigitRec.clw
..............................\DigitRec.cpp
..............................\DigitRec.dsp
..............................\DigitRec.dsw
..............................\DigitRec.h
..............................\DigitRec.rc
..............................\INPUT1.cpp
..............................\INPUT1.h
..............................\MainFrm.cpp
..............................\MainFrm.h
..............................\mydiblib.h
..............................\ReadMe.txt
..............................\Release
..............................\res
..............................\...\DigitRec.rc2
..............................\Resource.h
..............................\StdAfx.cpp
..............................\StdAfx.h
..............................\使用说明.txt
说明.txt
..............................\Bp.h
..............................\ChildView.cpp
..............................\ChildView.h
..............................\DBpParamater.cpp
..............................\DBpParamater.h
..............................\DIBAPI.CPP
..............................\DIBAPI.H
..............................\DigitRec.aps
..............................\DigitRec.clw
..............................\DigitRec.cpp
..............................\DigitRec.dsp
..............................\DigitRec.dsw
..............................\DigitRec.h
..............................\DigitRec.rc
..............................\INPUT1.cpp
..............................\INPUT1.h
..............................\MainFrm.cpp
..............................\MainFrm.h
..............................\mydiblib.h
..............................\ReadMe.txt
..............................\Release
..............................\res
..............................\...\DigitRec.rc2
..............................\Resource.h
..............................\StdAfx.cpp
..............................\StdAfx.h
..............................\使用说明.txt
说明.txt