// Use this for initialization
void Start()
{
String[] names = new string[] {"eng.cube.bigrams", "eng.cube.fold", "eng.cube.lm", "eng.cube.nn", "eng.cube.params", "eng.cube.size", "eng.cube.word-freq", "eng.tesseract_cube.nn", "eng.traineddata"};
String outputPath = Path.Combine(Application.persistentDataPath, "tessdata");
if (!Directory.Exists(outputPath))
Directory.CreateDirectory(outputPath);
foreach (String n in names)
{
TextAsset textAsset = Resources.Load<TextAsset>(Path.Combine("tessdata", n));
String filePath = Path.Combine(outputPath, n);
#if UNITY_METRO
UnityEngine.Windows.File.WriteAllBytes(filePath, textAsset.bytes);
#else
if (!File.Exists(filePath))
File.WriteAllBytes(filePath, textAsset.bytes);
#endif
}
_ocr = new Tesseract(outputPath, "eng", OcrEngineMode.TesseractCubeCombined);
Debug.Log("OCR engine loaded.");
Image<Bgr, Byte> img = new Image<Bgr, byte>(480, 200);
String message = "Hello, World";
CvInvoke.PutText(img, message, new Point(50, 100), Emgu.CV.CvEnum.FontFace.HersheySimplex, 1.0, new MCvScalar(255, 255, 255));
_ocr.Recognize(img);
Tesseract.Character[] characters = _ocr.GetCharacters();
foreach (Tesseract.Character c in characters)
{
CvInvoke.Rectangle(img, c.Region, new MCvScalar(255, 0, 0));
}
String messageOcr = _ocr.GetText().TrimEnd('\n', '\r'); // remove end of line from ocr-ed text
Debug.Log("Detected text: "+ message);
Texture2D texture = TextureConvert.InputArrayToTexture2D(img, FlipType.Vertical);
this.GetComponent<GUITexture>().texture = texture;
this.GetComponent<GUITexture>().pixelInset = new Rect(-img.Width / 2, -img.Height / 2, img.Width, img.Height);
}
private void btnAnalyzeImage_Click(object sender, EventArgs e)
{
if(picBox.Image == null)
{
MessageBox.Show("Load an image first!");
}
else
{
statusLabelOCR.Text = "Analyzing invoice image...";
Task.Run(() =>
{
using (var img = new Image<Bgr, byte>(path))
{
string tessdata = Environment.GetEnvironmentVariable("EMGU_ROOT") + @"\bin\tessdata";
using (var ocrProvider = new Tesseract(tessdata, "eng", OcrEngineMode.TesseractCubeCombined))
{
ocrProvider.Recognize(img);
string text = ocrProvider.GetText().TrimEnd();
rtbOcrResult.Invoke((MethodInvoker)delegate
{
statusLabelOCR.Text = "Analysis completed.";
rtbOcrResult.AppendText(text);
});
}
}
});
}
}
public static void test()
{
Tesseract _ocr = new Tesseract(@"C:\Users\yaoyichi\Desktop\emgucv-windows-universal-cuda 2.9.0.1922\", "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED);
string dir = @"C:\Users\yaoyichi\Desktop\";
string fn = "100890509_mc1024_k64.png";
Image<Bgr, Byte> gray = new Image<Bgr, byte>(dir + fn);
_ocr.Recognize(gray);
//TextRecognitionWorker trw = new TextRecognitionWorker();
//trw.ApplyABBYYOCR(dir, fn);
}
static void Main(string[] args)
{
using (var image = new Image<Bgr, byte>(Path.GetFullPath("text.png")))
{
using (var tess = new Tesseract("", "eng", OcrEngineMode.TesseractCubeCombined))
{
tess.Recognize(image);
var text = tess.GetText().TrimEnd();
}
}
}
private void TextRecogniser(Image image)
{
Emgu.CV.OCR.Tesseract tesseract = new Emgu.CV.OCR.Tesseract
(@"F:\Working Pack\c#\Scripter\Scripter\Templates\eng.traineddata", "eng",
OcrEngineMode.TesseractLstmCombined);
var tempImg = new Bitmap(image).ToImage <Gray, byte>();
tesseract.SetImage(tempImg);
tesseract.Recognize();
string response = tesseract.GetUTF8Text();
tesseract.Dispose();
}
public static Tesseract.Charactor[] DoOcr(Image<Gray, byte> img)
{
Tesseract.Charactor[] chars;
string text;
using (var tesseract = new Tesseract("tessdata", "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED)
)
{
tesseract.Recognize(img);
text = tesseract.GetText();
chars = tesseract.GetCharactors();
}
Console.WriteLine(text);
Console.ReadLine();
return chars;
}
private int recognizeSpeed(Rectangle rec, Image <Gray, byte> processedFrameSt)
{
Rectangle roi = new Rectangle(new Point(rec.Location.X, rec.Location.Y - 2), new Size(20, 14));
var imPart = processedFrameSt;
imPart.ROI = roi;
imPart = imPart.Copy();
//imPart = imPart.SmoothGaussian(1);
string tempDist = "";
if (tess != null)
{
tess.SetImage(imPart);
tess.Recognize();
noFiltDist = tess.GetUTF8Text();
for (int i = 0; i < noFiltDist.Length; i++)
{
if ((int)noFiltDist[i] > 47 && (int)noFiltDist[i] < 58)
{
tempDist += noFiltDist[i];
}
}
}
else
{
return(-666);
}
if (tempDist.Length >= 2)
{
if (distLess100)
{
tempDist = tempDist.Substring(0, 2);
}
filtDist = Convert.ToInt32(tempDist);
}
else
{
filtDist = -1;
}
return(filtDist);
}
/// <summary>
/// Tesseract OCR
/// </summary>
/// <param name="filteredPlate"></param>
/// <returns></returns>
private StringBuilder TesseractOCR(UMat filteredPlate)
{
Emgu.CV.OCR.Tesseract.Character[] words;
StringBuilder strBuilder = new StringBuilder();
using (UMat tmp = filteredPlate.Clone())
{
_ocr.SetImage(tmp);
_ocr.Recognize();
strBuilder.Append(_ocr.GetUTF8Text());
words = _ocr.GetCharacters();
//if (words.Length == 0) continue;
//for (int i = 0; i < words.Length; i++)
//{
// strBuilder.Append(words[i].Text);
//}
}
return(strBuilder);
}
//główne operacje na obrazie
public void ocr()
{
//otworzenie pliku
FileStream srcstream = new FileStream(pic_file, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);
//stworzenie bitmapy
Bitmap source = new Bitmap(srcstream);
//zmiana ustawień webform
Panel1.Visible = false;
Image1.Dispose();
Label2.Text = "Processing...";
Panel3.Visible = true;
//Preperation code
Bitmap ext = source;
//AForge.Imaging.Filters.
//Przekształcenie obrazu na skalę odcieni szarości - testować dla obrazów o różnej kolorystyce(opracować system wyznaczania parametrów filtru na podstawie RGB zdjęcia)
AForge.Imaging.Filters.Grayscale grScl = new AForge.Imaging.Filters.Grayscale(0.2125, 0.0154, 0.0721 );
source = grScl.Apply(source);
//Zwiększenie kontrastu
AForge.Imaging.Filters.ContrastStretch conCor = new AForge.Imaging.Filters.ContrastStretch();
source = conCor.Apply(source);
//Wyostrzenie
AForge.Imaging.Filters.Sharpen shp = new AForge.Imaging.Filters.Sharpen();
source = shp.Apply(source);
//Segmentation code
bool procesed = false;
// Image2.Width = 350;
// Image2.Height = (int)((source.Height * 200) / source.Width);
try
{
Emgu.CV.Image<Bgr, Byte> to_rec = new Emgu.CV.Image<Bgr, byte>(source);
Do_ocr = new Tesseract("tessdata", "eng", Tesseract.OcrEngineMode.OEM_DEFAULT);
try
{
Do_ocr.Recognize<Bgr>(to_rec);
//recognizedText.Text = ocr.GetText();
PastOCRBox.Text = Do_ocr.GetText();
// StatusBox.Text = "Finished! Ready for next one...";
Do_ocr.Dispose();
to_rec.Dispose();
}
catch (Exception exp)
{
Label2.Text = "Recognition error! " + exp.Message;
Do_ocr.Dispose();
return;
}
}
catch (Exception exp)
{
Label2.Text = "OCR engine failed! " + exp.Message;
return;
}
//czyszczenie z plików tymczasowych
// source.Save("D:\\test.bmp");
// ext.Save("D:\\testcor.bmp");
source.Dispose();
srcstream.Close();
srcstream.Dispose();
//System.IO.File.Delete(pic_file);
System.IO.File.Delete(Server.MapPath("~/img/prev.bmp"));
System.IO.File.Delete(Server.MapPath("~/img/tmp.bmp"));
//przygotować wygląd strony po rozpoznawaniu
Panel3.Visible = false;
Label1.Visible = false;
Panel0.Visible = false;
Panel5.Visible = false;
Panel4.Visible = true;
}
private static void Setup()
{
if (!_setup)
{
_ocr = new Tesseract("", "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED);
// If this is not done cost for any letters recognised which are not letters (i.e. false positives) will be zero
_ocr.Recognize(new Image<Gray, Byte>("tessdata/OCR initialise data.jpg"));
for (int i = 0; i < _mapHexColours.Length; i++ )
{
_mapColours.Add(ColorTranslator.FromHtml((_mapHexColours[i])));
}
_setup = true;
}
}
public List <string> ConvertImage(Bitmap image)
{
_tesseract.SetImage(new Image <Bgr, byte>(image));
_tesseract.Recognize();
return(_tesseract.GetLinesOfText());
}
static void Main(string[] args)
{
var files = Directory.GetFiles(@"d:\raw\classified\");
//var img = new Image<Rgb, byte>(files[0]);
var img = new Image<Emgu.CV.Structure.Gray, byte>(@"d:\raw\classified\test.jpg");
var _ocr = new Tesseract(@"D:\", "eng", OcrEngineMode.TesseractCubeCombined);
_ocr.SetVariable("tessedit_char_whitelist", "1234567890");
_ocr.Recognize(img);
var result = _ocr.GetCharacters();
}
public Receipt ConvertImage(Bitmap image)
{
_tesseract.SetImage(new Image <Bgr, byte> (image));
_tesseract.Recognize();
return(_tesseract.GetReceipt());
}
private void server()
{
int port = 8001;
IPAddress ipAd = IPAddress.Parse(ip);
// use local m/c IP address, and
// use the same in the client
ASCIIEncoding asen = new ASCIIEncoding();
/* Initializes the Listener */
TcpListener myList = new TcpListener(IPAddress.Any, port);
Console.WriteLine("The server is running at port 8001...");
Console.WriteLine("The local End point is :" +
myList.LocalEndpoint);
/* Start Listeneting at the specified port */
byte[] b = new byte[2000000];
myList.Start();
while (!stoped)
{
char[] recived = new char[2000000];
Console.WriteLine("Waiting for a connection.....");
TcpClient s = myList.AcceptTcpClient();
Console.WriteLine("Connection accepted " +s.Client.RemoteEndPoint);
NetworkStream stream = s.GetStream();
var reader = new StreamReader(stream);
var k = stream.Read(b, 0, 2000000);
Console.WriteLine("Recieved...");
ImageConverter conv = new ImageConverter();
Bitmap rec = new Bitmap((Bitmap)conv.ConvertFrom(b));
Console.WriteLine("Recognicion...");
Tesseract ocr = new Tesseract("tessdata", "pol+eng", Tesseract.OcrEngineMode.OEM_DEFAULT);
ocr.Recognize<Bgr>(new Emgu.CV.Image<Bgr, Byte>(rec));
string to_send_str = ocr.GetText();
ocr.Dispose();
Console.Write(to_send_str + "\n");
stream.Write(asen.GetBytes(to_send_str),0,to_send_str.Length);
Console.WriteLine("\nSent Acknowledgement");
/* clean up */
s.Close();
}
myList.Stop();
Console.WriteLine("Server stopped");
}
private void button5_Click(object sender, EventArgs e)
{
var _ocr = new Tesseract(@"D:\", "eng", OcrEngineMode.TesseractCubeCombined);
_ocr.SetVariable("tessedit_char_whitelist", "1234567890");
_ocr.Recognize(_inputArray);
var result = _ocr.GetCharacters().ToList();
var sb = new StringBuilder();
result.ForEach(c => sb.Append(c.Text));
label1.Text = sb.ToString();
}
private void FindLicensePlate(
VectorOfVectorOfPoint contours,
int[,] hierachy,
int idx,
IInputArray gray,
IInputArray canny,
List <IInputOutputArray> licensePlateImagesList,
List <IInputOutputArray> filteredLicensePlateImagesList,
List <RotatedRect> detectedLicensePlateRegionList,
List <String> licenses)
{
if (hierachy.Length != 0)
{
for (; idx >= 0; idx = hierachy[idx, 0])
{
int numberOfChildren = GetNumberOfChildren(hierachy, idx);
//if it does not contains any children (charactor), it is not a license plate region
if (numberOfChildren == 0)
{
continue;
}
using (VectorOfPoint contour = contours[idx])
{
if (CvInvoke.ContourArea(contour) > 400)
{
if (numberOfChildren < 3)
{
//If the contour has less than 3 children, it is not a license plate (assuming license plate has at least 3 charactor)
//However we should search the children of this contour to see if any of them is a license plate
FindLicensePlate(contours, hierachy, hierachy[idx, 2], gray, canny, licensePlateImagesList,
filteredLicensePlateImagesList, detectedLicensePlateRegionList, licenses);
continue;
}
RotatedRect box = CvInvoke.MinAreaRect(contour);
if (box.Angle < -45.0)
{
float tmp = box.Size.Width;
box.Size.Width = box.Size.Height;
box.Size.Height = tmp;
box.Angle += 90.0f;
}
else if (box.Angle > 45.0)
{
float tmp = box.Size.Width;
box.Size.Width = box.Size.Height;
box.Size.Height = tmp;
box.Angle -= 90.0f;
}
double whRatio = (double)box.Size.Width / box.Size.Height;
if (!(3.0 < whRatio && whRatio < 10.0))
//if (!(1.0 < whRatio && whRatio < 2.0))
{
//if the width height ratio is not in the specific range,it is not a license plate
//However we should search the children of this contour to see if any of them is a license plate
//Contour<Point> child = contours.VNext;
if (hierachy[idx, 2] > 0)
{
FindLicensePlate(contours, hierachy, hierachy[idx, 2], gray, canny, licensePlateImagesList,
filteredLicensePlateImagesList, detectedLicensePlateRegionList, licenses);
}
continue;
}
using (UMat tmp1 = new UMat())
using (UMat tmp2 = new UMat())
{
PointF[] srcCorners = box.GetVertices();
PointF[] destCorners = new PointF[] {
new PointF(0, box.Size.Height - 1),
new PointF(0, 0),
new PointF(box.Size.Width - 1, 0),
new PointF(box.Size.Width - 1, box.Size.Height - 1)
};
using (Mat rot = CvInvoke.GetAffineTransform(srcCorners, destCorners))
{
CvInvoke.WarpAffine(gray, tmp1, rot, Size.Round(box.Size));
}
//resize the license plate such that the front is ~ 10-12. This size of front results in better accuracy from tesseract
Size approxSize = new Size(240, 180);
double scale = Math.Min(approxSize.Width / box.Size.Width, approxSize.Height / box.Size.Height);
Size newSize = new Size((int)Math.Round(box.Size.Width * scale), (int)Math.Round(box.Size.Height * scale));
CvInvoke.Resize(tmp1, tmp2, newSize, 0, 0, Inter.Cubic);
//removes some pixels from the edge
int edgePixelSize = 3;
Rectangle newRoi = new Rectangle(new Point(edgePixelSize, edgePixelSize),
tmp2.Size - new Size(2 * edgePixelSize, 2 * edgePixelSize));
UMat plate = new UMat(tmp2, newRoi);
UMat filteredPlate = FilterPlate(plate);
//Tesseract.Character[] words;
StringBuilder strBuilder = new StringBuilder();
using (UMat tmp = filteredPlate.Clone())
{
Emgu.CV.OCR.Tesseract.Character[] words;
_ocr.Recognize(tmp);
strBuilder.Append(_ocr.GetText());
words = _ocr.GetCharacters();
if (words.Length == 0)
{
continue;
}
for (int i = 0; i < words.Length; i++)
{
strBuilder.Append(words[i].Text);
}
}
licenses.Add(strBuilder.ToString());
//изображения номеров
licensePlateImagesList.Add(plate);
filteredLicensePlateImagesList.Add(filteredPlate);
detectedLicensePlateRegionList.Add(box);
}
}
}
}
}
}