c＃中的车牌识别 [英] License plate recognation in c#

问题描述

我需要用c＃进行水平和垂直投影并进行二值化但是我不能。你可以帮助我吗？

做这三步

1-二值化

2-水平投影

3 - 垂直投影

请快速

解决方案

查看以下文章：

使用神经网络创建光学字符识别（OCR）应用程序 [ ^ ]

用于识别C＃中手写数字的神经网络 [< a href =http://www.codeproject.com/Articles/143059/Neural-Network-for-Recognition-of-Handwritten-Digitarget =_ blanktitle =New Window> ^ ]



祝你好运

Espen Harlinn

你需要的是所谓的OCR，光学字符识别。请参阅：

http://en.wikipedia.org/wiki/Optical_character_recognition [< a href =http://en.wikipedia.org/wiki/Optical_character_recognitiontarget =_ blanktitle =New Window> ^ ]。



不幸的是，我必须警告你：我从来没有找到任何完美的开源OCR解决方案，但它对于车牌号码来说可能已经足够了。我喜欢的CodeProject解决方案很少，但是，为了最好的知识，它们都是不完整的，需要大量的工作来制作一个有效的应用程序，它们适用于.NET，而不是Java。



请参阅这些CodeProject文章：



神经网络OCR [ ^ ]，
使用神经网络创建光学字符识别（OCR）应用程序 [ ^ ]，
神经网络分类器 [ ^ ]，

使用链码的光学字符识别（OCR）中的AC＃项目 [ ^ ]，

Unicode光学字符识别 [ ^ ]，

Hebb神经网络 [ ^ ]，

C ++中的反向传播人工神经网络 [ ^ ]，

OCR线路检测 [ ^ ]。



也许有一些我不熟悉的新项目;因此，如果您在CodeProject和其他地方进行自己的搜索，则不会受到影响。如果您发现有什么好的话，请回复此答案的评论。







对，您可能还需要在OCR之前使用一些通用图像处理。我推荐由 Andrew Kirillov 编写的开源库AForge.NET，一个CodeProject成员：

http://en.wikipedia.org/wiki/AForge.NET [ ^ ]，

http://www.aforgenet.com/ [ ^ ]。



请参阅CodeProject上的安德鲁文章：

http://www.codeproject.com/Articles/Andrew-Kirillov#articles [ ^ ]。

-SA

您也可以尝试 Emgu [<一个人f =http://www.emgu.com/wiki/index.php/Main_Pagetarget =_ blanktitle =新窗口> ^ ]框架，它实现了大多数图像处理算法

License_Plate_Recognition_in_CSharp [ ^ ]

i need to do horizontal and vertical projection with c# and do binarization but i cant. can you help me ?
to do this three steps
1- binarization
2- horizontal projection
3- vertical projection
please quickly

解决方案

Have a look at the following articles:
Creating Optical Character Recognition (OCR) applications using Neural Networks[^]
Neural Network for Recognition of Handwritten Digits in C#[^]

Best regards
Espen Harlinn

What you need is called OCR, "Optical Character Recognition". Please see:
http://en.wikipedia.org/wiki/Optical_character_recognition[^].

Unfortunately, I must warn you: I never found any Open-Source OCR solutions which would be perfect, but it could be good enough for just the license plate number. There are few CodeProject solutions I like, but, to best of knowledge, they are all incomplete, would need serious amount of work to make a working application out of them, and they are for .NET, not Java.

Please see these CodeProject articles:

Neural Network OCR[^],
Creating Optical Character Recognition (OCR) applications using Neural Networks[^],
Neural Network Classifier[^],
A C# Project in Optical Character Recognition (OCR) Using Chain Code[^],
Unicode Optical Character Recognition[^],
Hebb neural network[^],
Backpropagation Artificial Neural Network in C++[^],
OCR Line Detection[^].

Maybe there are newer projects I''m not familiar with; so it would not hurt if you do your own search in CodeProject and elsewhere. Please, if you find something good, please reply in the comment to this answer.

[EDIT: in response to a follow-up question to Solution 1:]

Right, you might also need some general image processing to be used before OCR. I recommend the open-source library AForge.NET written by Andrew Kirillov, a CodeProject member:
http://en.wikipedia.org/wiki/AForge.NET[^],
http://www.aforgenet.com/[^].

Please see Andrews articles at CodeProject:
http://www.codeproject.com/Articles/Andrew-Kirillov#articles[^].

—SA

You may also try Emgu [^] framework which implements most of the image processing algorithms
License_Plate_Recognition_in_CSharp[^]

这篇关于c＃中的车牌识别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！