public static void GetIMagesOnly(string FileDirectory)
{
var ext = new List <string> {
".jpg", ".gif", ".png", "tif"
};
var fileEntries = Directory.GetFiles(FileDirectory, "*.*", SearchOption.AllDirectories)
.Where(s => ext.Any(e => s.EndsWith(e)));
foreach (string fileName in fileEntries)
{
Console.WriteLine("Image file '{0}'.", fileName);
//Console.WriteLine(Path.GetFileName(fileName));// used to get only file name
// PerformingOCR.DoOCR1(fileName);
ImagePreProcessing.EnhanceImageQuality(fileName.ToString());
// Console.ReadLine();
}
fileEntries = Directory.GetFiles(@"C:\OCR\EnhancedImage", "*.*", SearchOption.AllDirectories)
.Where(s => ext.Any(e => s.EndsWith(e)));
var InvoiceList = new List <Invoice>();
foreach (string fileName in fileEntries)
{
Console.WriteLine("Image file '{0}'.", fileName);
var pageItem = PerformingOCR.DoOCR1(fileName);
Identify removeSpace = new Identify();
pageItem = removeSpace.RemoveSpace(pageItem);
Invoice ck = PopInvoice.poplateInvoice(pageItem, fileName);
InvoiceList.Add(ck);
}
List <String> lines = new List <String>();
foreach (Invoice invoice in InvoiceList)
{
lines.Add("Invocie File Name" + " " + invoice.InvoiceID);
lines.Add("Invoice Date" + " " + invoice.InvoiceDate);
lines.Add("VendorName" + " " + invoice.VendorName);
lines.Add(" " + "QTY" + " " + " " + "Amount " + " " + " " + "Item" + " ");
foreach (Lineitem lineitem in invoice.Lineitems)
{
lines.Add(" " + lineitem.ItemQty + " " + " " + lineitem.ItemAmount + " " + lineitem.ItemName);
}
lines.Add("Total Amount" + " " + invoice.TotalAmount);
lines.Add("****************************************************************************");
}
// WriteAllLines creates a file, writes a collection of strings to the file,
// and then closes the file. You do NOT need to call Flush() or Close().
System.IO.File.WriteAllLines(@"C:\OCR\EnhancedImage\OcrResult.txt", lines);
Console.ReadLine();
}
public static List <row> DoOCR1(string imageDir)
{
if (imageDir != null)//&& imageDir.fil > 0) check file exist
{
var Rowlist = new List <row>();
using (var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default))
{
// have to load Pix via a bitmap since Pix doesn't support loading a stream.
engine.SetVariable("tessedit_char_whitelist", "16.00ABCDEFGHIJKLMNOPQRSTUVWXYZ(quick) brown { fox} jumps!over the $3,456.78 < lazy >: #90 dog & duck/goose, as 12.5% of Email from [email protected] is spam?");
// engine.DefaultPageSegMode = PageSegMode.AutoOsd;
// engine.SetVariable("tessedit_char_whitelist", "0123456789,/ABCDEFGHIJKLMNOPQRSTUVWXYZ.abcdefghijklmnopqrstuvwxyz():!'$");
Pix pixImage = Pix.LoadFromFile(imageDir);
// pixImage = pixImage.Deskew();
//Scew scew;
//pixImage = pixImage.Deskew(new ScewSweep(range: 90), Pix.DefaultBinarySearchReduction, Pix.DefaultBinaryThreshold, out scew);
//pixImage.Save(@"C:\OCR\EnhancedImage\deskew.tiff", ImageFormat.Tiff);
using (var image = new System.Drawing.Bitmap(imageDir))
{
using (var pix = PixConverter.ToPix(image))
{
// pix.Deskew();
using (var page = engine.Process(pix))
{
Console.WriteLine("Mean confidence: {0:p}", page.GetMeanConfidence());
Console.WriteLine(page.GetText());
var i = 1;
var j = 1;
using (var iter = page.GetIterator())
{
iter.Begin();
do
{
do
{
// Console.WriteLine("in-looop");
do
{
Console.WriteLine("Line {0}", i);
j = 1;
do
{
//if (iter.GetText(PageIteratorLevel.Word) != "")
// strWord = iter.GetText(PageIteratorLevel.Word).GetType().GetGenericTypeDefinition();
Console.WriteLine("word:{0} ", iter.GetText(PageIteratorLevel.Word));
Identify strType = new Identify();
Rowlist.Add(new row
{
line = i,
colomun = j,
type = Convert.ToInt16(strType.StringType(iter.GetText(PageIteratorLevel.Word))),
word = iter.GetText(PageIteratorLevel.Word)
});
j = j + 1;
} while (iter.Next(PageIteratorLevel.TextLine, PageIteratorLevel.Word));
i++;
} while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.TextLine));
} while (iter.Next(PageIteratorLevel.Block, PageIteratorLevel.Para));
} while (iter.Next(PageIteratorLevel.Block));
var k = Rowlist;
}
}
}
}
}
return(Rowlist);
}
else
{
return(null);
}
}
