Microsoft Office Document Imaging 虚拟打印机
Extracting Text From Image
The following program shows you how to extract text from image. For this you'll have add reference (under COM tab) of "Microsoft Office Document Imaging Library". If you wouldn't find this reference then install microsoft office version 2007 and go to customize and choose Office tools and check the "Microsoft Office Document Imaging" and install it. Now after doing this go to (add reference and under COM tab) add its reference and use it.
//Extract button working, text is extracted from image
private void btnExtract_Click(object sender, EventArgs e)
{
MODI.Document doc = new MODI.Document();
doc.Create(getFileName);
doc.OCR(MODI.MiLANGUAGES.miLANG_ENGLISH, true, true);
MODI.Image img = (MODI.Image)doc.Images[0];
MODI.Layout layout = img.Layout;
for (int i = 0; i < layout.Words.Count; i++)
{
MODI.Word word = (MODI.Word)layout.Words[i];
if (extractedText.Length > 0)
{
extractedText += " ";
}
extractedText += word.Text;
richTextBox1.Text = extractedText;
}
}