C # Image recognition (21 languages supported)

Image recognition technology to a few days has been very mature, but the relevant information is very few, in order to facilitate this summary (C # Implementation), convenient for friends to consult, but also to make a mark for themselves.

The use of image recognition: Many people use it to crack the site's verification code, used to achieve the purpose of automatic swipe or bulk registration, but I think it is the most attractive to me is to let some writing, automatically recognize the text on the computer, such as hand-drawn contracts, modified written papers or documents, Monthly spending invoices need to be recorded on the computer or aggregated information, journal articles to be transferred to the computer and so on, we now do not have a headache to write them on the computer again.

In this paper, we introduce two kinds of popular and mature recognition methods:

Way one, ASPRISE-OCR realization.

Way two, Microsoft office Document Imaging (Office 2007) components are implemented.

Method one, ASPRISE-OCR use.

ASPRISE-OCR:

Http://asprise.com/product/ocr/download.php?lang=csharp  

The 3 DLLs that need to be used are AspriseOCR.dll, DevIL.dll, ILU.dll.

It is important to note that these several. dll is the VC write reference to be used in the program with DllImport reference, the key code:

[DllImport ("AspriseOCR.dll", EntryPoint = "OCR", CallingConvention = callingconvention.cdecl)]

public static extern IntPtr OCR (string file, int type);

[DllImport ("AspriseOCR.dll", EntryPoint = "Ocrpart", CallingConvention = callingconvention.cdecl)]

static extern IntPtr Ocrpart (string file, int type, int startX, int starty, int width, int height);

[DllImport ("AspriseOCR.dll", EntryPoint = "Ocrbarcodes", CallingConvention = callingconvention.cdecl)]

static extern IntPtr ocrbarcodes (string file, int type);

[DllImport ("AspriseOCR.dll", EntryPoint = "Ocrpartbarcodes", CallingConvention = callingconvention.cdecl)]

static extern IntPtr ocrpartbarcodes (string file, int type, int startX, int starty, int width, int height);

The calling code is simply one sentence:

MessageBox.Show (Marshal.ptrtostringansi (Ocrpart (Img_path,-1, StartX, starty, width, height)));

Where Img_path: For the picture path, StartX, starty coordinates are 0, width, height picture width and height.

Way two, Microsoft office Document Imaging (Office 2007) components are implemented.

Before using the imaging component compatibility is not very good, the use of Win 7 Office 2007 must be on the office of the SP1 or SP2 patch, read Chinese only line.

SP1 patch address (226M):

http://download.microsoft.com/download/1/6/5/1659d607-8696-4001-8072-efaedd70dd30/ Office2007sp1-kb936982-fullfile-zh-cn.exe

SP2 patch address (301 MB):

http://download.microsoft.com/download/A/3/9/A39E919E-AFA8-4128-9249-51629206C70F/ Office2007sp2-kb953195-fullfile-zh-cn.exe

Add a component reference to the project,

Using code:

MODI. Document doc = new MODI. Document ();

Doc. Create (Img_path);

MODI. Image Image;

MODI. Layout layout;

Doc.  OCR (MODI.MiLANGUAGES.miLANG_CHINESE_SIMPLIFIED, True, true); Identify Simplified Chinese

for (int i = 0; i < Doc. Images.count; i++)

{

Image = (MODI. Image) Doc. Images[i];

Layout = image. Layout;

Sb. Append (layout. Text);

}

MessageBox.Show (sb.) ToString ());

Where Img_path is the picture path, Modi.milanguages is the text type enumeration that reads the picture.

This article source:Http://files.cnblogs.com/stone_w/OCR.rar

C # Image recognition (21 languages supported)