NET 2.0 OCR Text recognition technology (Tesseract engine)

I. Introduction to OCR see Http://baike.baidu.com/view/17761.htm?fr=ala0_1 Everyone reference, I was the first to know so, hehe. Master laughed at

Now there are many OCR engines on the market, but most of them are charged and expensive. Not suitable for us to study.

And today we talk about the tesseract is open-source products, more suitable for everyone's taste it. And Tesseract is currently a high recognition rate of OCR, no more than other engines

Bad. Online Introduction Tessnet2 is also the time of the third-ranking recognition engine, but slowly not maintenance, is now Google in maintenance, we all know that Google

In the electronic library, every day there are different types of books are scanned into electronic version, and the next step of work is what ... We can associate.

Tessnet2 is developed with VC + +, the most is the generation of Tessnet2.dll, we can call the internal concrete class library implementation recognition through. NET.

Use of Tessnet2:

1. Add Tessnet2.dll to the VS Bin directory, just as you would add a. NET assembly. Http://files.cnblogs.com/zhuxiangyu/tessnet2_32.rar click the link to download Tessnet2.dll

2. Use Tessnet2 to identify

　

Bitmap image = Newbitmap ("eurotext.tif");//Identifying Images
Tessnet2. TESSERACTOCR = new Tessnet2. Tesseract ();//declare an OCR class
Ocr. SetVariable ("Tessedit_char_whitelist", "0123456789"); Sets the recognition variable, which currently only recognizes numbers.
Ocr. Init (@ "C:\Temp", "Fra", false); Applies the current language pack. Note that Tessnet2 is supported in multi-lingual. Language pack Download Link: http://code.google.com/p/tesseract-ocr/downloads/list
List<tessnet2. word> result = OCR. DOOCR (image, Rectangle.empty);//Perform a recognition operation
foreach (Tessnet2. Word word in result)//traversal recognition result.
Console.WriteLine ("{0}: {1}", Word. Confidence, Word. Text);

Let's see how easy it is to use. Give everyone an example http://files.cnblogs.com/zhuxiangyu/Tessnet2example.rar to test.

NET 2.0 OCR Text recognition technology (Tesseract engine)