/// <summary>
/// Extract text from document with specific Ocr Mode
/// </summary>
/// <param name="inputDocument"></param>
/// <param name="oCRMode"></param>
/// <returns></returns>
private static string _ExtractTextWithSpecificOCRMode(string inputDocument, OCRMode ocrMode)
{
// Location of language data files
string ocrLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// OCR language
string ocrLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
// Find more language files at https://github.com/bytescout/ocrdata
// Create TextExtractor instance
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document to TextExtractor
textExtractor.LoadDocumentFromFile(inputDocument);
// Specify Ocr Mode
textExtractor.OCRMode = ocrMode;
// Ocr language data folder path and language
textExtractor.OCRLanguageDataFolder = ocrLanguageDataFolder;
textExtractor.OCRLanguage = ocrLanguage;
// Return extracted text
return(textExtractor.GetText());
}
}
protected void Page_Load(object sender, EventArgs e)
{
try
{
string strImageName = "";
int iFileLength;
HttpFileCollection files = HttpContext.Current.Request.Files;
HttpPostedFile uploadfile = files["RemoteFile"];
if (uploadfile != null)
{
strImageName = uploadfile.FileName;
iFileLength = uploadfile.ContentLength;
Byte[] inputBuffer = new Byte[iFileLength];
System.IO.Stream inputStream;
inputStream = uploadfile.InputStream;
inputStream.Read(inputBuffer, 0, iFileLength);
string strLanguage = "0";
try
{
strLanguage = HttpContext.Current.Request.Form["OCRLanguage"].ToString();
}
catch { }
string strFormat = "0";
try
{
strFormat = HttpContext.Current.Request.Form["FileFormat"].ToString();
}
catch { }
string strReturnValue = "";
try
{
byte[] content = OCRMode.OCR(inputBuffer, strLanguage, Convert.ToInt32(strFormat));
string strFileName = SaveOCRContentAsFile(content, Convert.ToInt32(strFormat));
strReturnValue = "OK;" + "DownLoadOCR.aspx?FileId=" + Server.UrlEncode(strFileName);
}
catch (Exception exp)
{
strReturnValue = "EXP;" + exp.Message.ToString();
}
finally
{
}
Response.Write(strReturnValue);
}
}
catch (Exception exp)
{
Response.Write("EXP;" + exp.Message.ToString() + "; 0;");
}
}
public static void OCRSetup(OCRMode mode)
{
string dir = Environment.CurrentDirectory + @"\Modules\OCR\tessdata";
switch (mode)
{
case OCRMode.NUMBERS:
_ocr = new Tesseract(dir, "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_ONLY);
_ocr.SetVariable("tessedit_char_whitelist", "1234567890");
break;
case OCRMode.COMBINED:
_ocr = new Tesseract(dir, "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED);
break;
}
OCRRoutine.DoWork += new DoWorkEventHandler(OCRRoutine_doWork);
OCRRoutine.ProgressChanged += new ProgressChangedEventHandler(OCRRoutine_ProgressChanged);
OCRRoutine.RunWorkerCompleted += new RunWorkerCompletedEventHandler(OCRRoutine_WorkerCompleted);
OCRRoutine.WorkerReportsProgress = true;
}
private static String OcrImage(Tesseract ocr, Mat image, OCRMode mode, Mat imageColor)
{
Bgr drawCharColor = new Bgr(Color.Red);
if (image.NumberOfChannels == 1)
{
CvInvoke.CvtColor(image, imageColor, ColorConversion.Gray2Bgr);
}
else
{
image.CopyTo(imageColor);
}
if (mode == OCRMode.FullPage)
{
ocr.SetImage(imageColor);
if (ocr.Recognize() != 0)
{
throw new Exception("Failed to recognizer image");
}
Tesseract.Character[] characters = ocr.GetCharacters();
if (characters.Length == 0)
{
Mat imgGrey = new Mat();
CvInvoke.CvtColor(image, imgGrey, ColorConversion.Bgr2Gray);
Mat imgThresholded = new Mat();
CvInvoke.Threshold(imgGrey, imgThresholded, 65, 255, ThresholdType.Binary);
ocr.SetImage(imgThresholded);
characters = ocr.GetCharacters();
imageColor = imgThresholded;
if (characters.Length == 0)
{
CvInvoke.Threshold(image, imgThresholded, 190, 255, ThresholdType.Binary);
ocr.SetImage(imgThresholded);
characters = ocr.GetCharacters();
imageColor = imgThresholded;
}
}
foreach (Tesseract.Character c in characters)
{
CvInvoke.Rectangle(imageColor, c.Region, drawCharColor.MCvScalar);
}
return(ocr.GetUTF8Text());
}
else
{
bool checkInvert = true;
Rectangle[] regions;
using (
ERFilterNM1 er1 = new ERFilterNM1("trained_classifierNM1.xml", 8, 0.00025f, 0.13f, 0.4f, true, 0.1f))
using (ERFilterNM2 er2 = new ERFilterNM2("trained_classifierNM2.xml", 0.3f))
{
int channelCount = image.NumberOfChannels;
UMat[] channels = new UMat[checkInvert ? channelCount * 2 : channelCount];
for (int i = 0; i < channelCount; i++)
{
UMat c = new UMat();
CvInvoke.ExtractChannel(image, c, i);
channels[i] = c;
}
if (checkInvert)
{
for (int i = 0; i < channelCount; i++)
{
UMat c = new UMat();
CvInvoke.BitwiseNot(channels[i], c);
channels[i + channelCount] = c;
}
}
VectorOfERStat[] regionVecs = new VectorOfERStat[channels.Length];
for (int i = 0; i < regionVecs.Length; i++)
{
regionVecs[i] = new VectorOfERStat();
}
try
{
for (int i = 0; i < channels.Length; i++)
{
er1.Run(channels[i], regionVecs[i]);
er2.Run(channels[i], regionVecs[i]);
}
using (VectorOfUMat vm = new VectorOfUMat(channels))
{
regions = ERFilter.ERGrouping(image, vm, regionVecs, ERFilter.GroupingMethod.OrientationHoriz,
"trained_classifier_erGrouping.xml", 0.5f);
}
}
finally
{
foreach (UMat tmp in channels)
{
if (tmp != null)
{
tmp.Dispose();
}
}
foreach (VectorOfERStat tmp in regionVecs)
{
if (tmp != null)
{
tmp.Dispose();
}
}
}
Rectangle imageRegion = new Rectangle(Point.Empty, imageColor.Size);
for (int i = 0; i < regions.Length; i++)
{
Rectangle r = ScaleRectangle(regions[i], 1.1);
r.Intersect(imageRegion);
regions[i] = r;
}
}
List <Tesseract.Character> allChars = new List <Tesseract.Character>();
String allText = String.Empty;
foreach (Rectangle rect in regions)
{
using (Mat region = new Mat(image, rect))
{
ocr.SetImage(region);
if (ocr.Recognize() != 0)
{
throw new Exception("Failed to recognize image");
}
Tesseract.Character[] characters = ocr.GetCharacters();
//convert the coordinates from the local region to global
for (int i = 0; i < characters.Length; i++)
{
Rectangle charRegion = characters[i].Region;
charRegion.Offset(rect.Location);
characters[i].Region = charRegion;
}
allChars.AddRange(characters);
allText += ocr.GetUTF8Text() + Environment.NewLine;
}
}
Bgr drawRegionColor = new Bgr(Color.Red);
foreach (Rectangle rect in regions)
{
CvInvoke.Rectangle(imageColor, rect, drawRegionColor.MCvScalar);
}
foreach (Tesseract.Character c in allChars)
{
CvInvoke.Rectangle(imageColor, c.Region, drawCharColor.MCvScalar);
}
return(allText);
}
}