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);
}
}
private void loadImageButton_Click(object sender, EventArgs e)
{
if (openImageFileDialog.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
fileNameTextBox.Text = openImageFileDialog.FileName;
imageBox1.Image = null;
ocrTextBox.Text = String.Empty;
hocrTextBox.Text = String.Empty;
Bgr drawCharColor = new Bgr(Color.Blue);
try
{
Mat image = new Mat(openImageFileDialog.FileName, ImreadModes.AnyColor);
Mat imageColor = new Mat();
if (image.NumberOfChannels == 1)
{
CvInvoke.CvtColor(image, imageColor, ColorConversion.Gray2Bgr);
}
else
{
image.CopyTo(imageColor);
}
if (Mode == OCRMode.FullPage)
{
_ocr.Recognize(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.Recognize(imgThresholded);
characters = _ocr.GetCharacters();
imageColor = imgThresholded;
if (characters.Length == 0)
{
CvInvoke.Threshold(image, imgThresholded, 190, 255, ThresholdType.Binary);
_ocr.Recognize(imgThresholded);
characters = _ocr.GetCharacters();
imageColor = imgThresholded;
}
}
foreach (Tesseract.Character c in characters)
{
CvInvoke.Rectangle(imageColor, c.Region, drawCharColor.MCvScalar);
}
imageBox1.Image = imageColor;
String text = _ocr.GetText();
ocrTextBox.Text = text;
String hocrText = _ocr.GetHOCRText();
hocrTextBox.Text = hocrText;
}
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.Recognize(region);
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.GetText() + 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);
}
imageBox1.Image = imageColor;
ocrTextBox.Text = allText;
}
}
catch (Exception exception)
{
MessageBox.Show(exception.Message);
}
}
}
public string Recognize(Mat image)
{
Rectangle[] regions;
Bgr drawCharColor = new Bgr(Color.Red);
using (var er1 = new ERFilterNM1("Assets\\trained_classifierNM1.xml", 8, 0.00025f, 0.13f, 0.4f, true, 0.1f)) {
using (var er2 = new ERFilterNM2("Assets\\trained_classifierNM2.xml", 0.3f)) {
var channelCount = image.NumberOfChannels;
var channels = new UMat[channelCount * 2];
for (int i = 0; i < channelCount; i++)
{
var c = new UMat();
CvInvoke.ExtractChannel(image, c, i);
channels[i] = c;
}
for (int i = 0; i < channelCount; i++)
{
var c = new UMat();
CvInvoke.BitwiseNot(channels[i], c);
channels[i + channelCount] = c;
}
var 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 (var vm = new VectorOfUMat(channels)) {
regions = ERFilter.ERGrouping(image, vm, regionVecs, ERFilter.GroupingMethod.OrientationHoriz,
"Assets\\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, image.Size);
for (int i = 0; i < regions.Length; i++)
{
Rectangle r = ScaleRectangle(regions[i], 1.1);
r.Intersect(imageRegion);
regions[i] = r;
}
}
var 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)
{
return(null);
}
//var 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() + "|";
}
}
//Bgr drawRegionColor = new Bgr(Color.Red);
//foreach (Rectangle rect in regions) {
// CvInvoke.Rectangle(image, rect, drawRegionColor.MCvScalar);
//}
//foreach (Tesseract.Character c in allChars) {
// CvInvoke.Rectangle(image, c.Region, drawCharColor.MCvScalar);
//}
return(allText);
}
}
/// <summary>
/// Takes image on input and returns the selected regions in a vector of ERStat only distinctive ERs which correspond to characters are selected by a sequential classifier
/// </summary>
/// <param name="image">Sinle channel image CV_8UC1</param>
/// <param name="regions">Output for the 1st stage and Input/Output for the 2nd. The selected Extremal Regions are stored here.</param>
public void Run(IInputArray image, VectorOfERStat regions)
{
using (InputArray iaImage = image.GetInputArray())
CvERFilterRun(_ptr, iaImage, regions);
}
public void Run(Image <Gray, Byte> image, VectorOfERStat regions)
{
CvInvoke.CvERFilterRun(_ptr, image, regions);
}
