static void example3()
{
string dataPath = "./tessdata/";
string language = "eng";
string inputFile = "./input.png";
OcrEngineMode oem = OcrEngineMode.DEFAULT;
PageSegmentationMode psm = PageSegmentationMode.AUTO_OSD;
TessBaseAPI tessBaseAPI = new TessBaseAPI();
// Initialize tesseract-ocr
if (!tessBaseAPI.Init(dataPath, language, oem))
{
throw new Exception("Could not initialize tesseract.");
}
// Set the Page Segmentation mode
tessBaseAPI.SetPageSegMode(psm);
// Set the input image
Pix pix = tessBaseAPI.SetImage(inputFile);
// Recognize image
tessBaseAPI.Recognize();
ResultIterator resultIterator = tessBaseAPI.GetIterator();
// extract text from result iterator
StringBuilder stringBuilder = new StringBuilder();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
stringBuilder.Append(resultIterator.GetUTF8Text(pageIteratorLevel));
} while (resultIterator.Next(pageIteratorLevel));
tessBaseAPI.Dispose();
pix.Dispose();
}
public void /*Image*/ GetTextFromImage(IWebElement element, string uniqueName)
{
Screenshot screenshot = ((ITakesScreenshot)Driver).GetScreenshot();
string pth = Assembly.GetCallingAssembly().CodeBase;
string finalpth = pth.Substring(0, pth.LastIndexOf("bin")) + "Screenshots/" + uniqueName + ".jpeg";
string localpath = new Uri(finalpth).LocalPath;
screenshot.SaveAsFile(localpath, ScreenshotImageFormat.Jpeg);
Image img = Image.FromFile(localpath /*uniqueName*/);
Rectangle rect = new Rectangle();
if (element != null)
{
// Get the Width and Height of the WebElement using
int width = element.Size.Width;
int height = element.Size.Height;
// Get the Location of WebElement in a Point.
// This will provide X & Y co-ordinates of the WebElement
Point p = element.Location;
// Create a rectangle using Width, Height and element location
rect = new Rectangle(p.X, p.Y, width, height);
}
//croping the image based on rect.
Bitmap bmpImage = new Bitmap(img);
var cropedImag = bmpImage.Clone(rect, bmpImage.PixelFormat);
string dataPath = @"C:\Betsold\AutomationTesting\Tests\testdata\";
string language = "eng";
string imgPath = @"C:\Betsold\AutomationTesting\Tests\Screenshots\logo-test.jpeg";
OcrEngineMode oem = OcrEngineMode.LSTM_ONLY;
PageSegmentationMode psm = PageSegmentationMode.AUTO;
TessBaseAPI tessBaseAPI = new TessBaseAPI(dataPath, language, oem, psm);
// Set the input image
tessBaseAPI.SetImage(imgPath);
var processedImage = tessBaseAPI.GetThresholdedImage();
processedImage.Write(@"C:\Users\ibozhinovski\Desktop\", ImageFileFormatTypes.IFF_JFIF_JPEG);
// Recognize image
tessBaseAPI.Recognize();
ResultIterator resultIterator = tessBaseAPI.GetIterator();
// Extract text from result iterator
StringBuilder text = new StringBuilder();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
text.Append(resultIterator.GetUTF8Text(pageIteratorLevel));
} while (resultIterator.Next(pageIteratorLevel));
tessBaseAPI.Dispose();
Console.Read();
/*
* // croping the image based on rect.
* Bitmap bmpImage = new Bitmap(img);
* var cropedImag = bmpImage.Clone(rect, bmpImage.PixelFormat);
*
* var ocr = new TesseractEngine("./testdata", "eng");
*
* var page = ocr.Process(cropedImag);
*
* var result = page.GetText();
*
* Console.WriteLine(result);
*/
}
protected override ApiResult ProcessClientQueueMessage(ImageArtifact message)
{
BitmapData bData = message.Image.LockBits(
new Rectangle(0, 0, message.Image.Width, message.Image.Height), ImageLockMode.ReadOnly, message.Image.PixelFormat);
int w = bData.Width, h = bData.Height, bpp = Image.GetPixelFormatSize(bData.PixelFormat) / 8;
unsafe
{
TesseractImage.SetImage(new UIntPtr(bData.Scan0.ToPointer()), w, h, bpp, bData.Stride);
}
Pix = TesseractImage.GetInputImage();
Debug("Pix has width: {0} height: {1} depth: {2} xres: {3} yres: {4}.", Pix.Width, Pix.Height, Pix.Depth,
Pix.XRes, Pix.YRes);
List <string> text;
using (var op = Begin("Tesseract OCR (fast)"))
{
TesseractImage.Recognize();
ResultIterator resultIterator = TesseractImage.GetIterator();
text = new List <string>();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
string ant = TextArtifact.GetAlphaNumericString(resultIterator.GetUTF8Text(pageIteratorLevel));
ant = string.Join(" ",
ant.Split(new[] { ' ', '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries)
.Where(word => TextArtifact.IsNumber(word) || word.Length > 3 || Pipeline.Dictionaries["common_words_en_3grams"].Contains(word)))
.Trim();
if (ant.IsEmpty())
{
continue;
}
else
{
text.Add(ant);
}
}while (resultIterator.Next(pageIteratorLevel));
if (text.Count > 0)
{
string alltext = text.Aggregate((s1, s2) => s1 + " " + s2).Trim();
if (text.Count < 7)
{
Info("Artifact id {0} is likely a photo or non-text image.", message.Id);
}
else
{
message.OCRText = text;
Info("OCR Text: {0}", alltext);
}
}
else
{
Info("No text recognized in artifact id {0}.", message.Id);
}
op.Complete();
}
message.Image.UnlockBits(bData);
if (text.Count >= 7)
{
TextArtifact artifact = new TextArtifact(message.Name + ".txt", string.Join(Environment.NewLine, text.ToArray()));
artifact.Source = message.Source;
artifact.CurrentProcess = message.CurrentProcess;
artifact.CurrentWindowTitle = message.CurrentWindowTitle;
artifact.Image = message;
message.TextArtifact = artifact;
EnqueueMessage(artifact);
Info("{0} added artifact id {1} of type {2} from artifact {3}.", Name, artifact.Id, artifact.GetType(),
message.Id);
}
return(ApiResult.Success);
}
protected override ApiResult ProcessClientQueueMessage(ImageArtifact message)
{
BitmapData bData = message.Image.LockBits(
new Rectangle(0, 0, message.Image.Width, message.Image.Height), ImageLockMode.ReadOnly, message.Image.PixelFormat);
int w = bData.Width, h = bData.Height, bpp = Image.GetPixelFormatSize(bData.PixelFormat) / 8;
unsafe
{
TesseractImage.SetImage(new UIntPtr(bData.Scan0.ToPointer()), w, h, bpp, bData.Stride);
}
Pix = TesseractImage.GetInputImage();
Debug("Pix has width: {0} height: {1} depth: {2} xres: {3} yres: {4}.", Pix.Width, Pix.Height, Pix.Depth,
Pix.XRes, Pix.YRes);
List <string> text;
using (var op = Begin("Tesseract OCR (fast)"))
{
TesseractImage.Recognize();
ResultIterator resultIterator = TesseractImage.GetIterator();
text = new List <string>();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_PARA;
do
{
string r = resultIterator.GetUTF8Text(pageIteratorLevel);
if (r.IsEmpty())
{
continue;
}
text.Add(r.Trim());
}while (resultIterator.Next(pageIteratorLevel));
if (text.Count > 0)
{
string alltext = text.Aggregate((s1, s2) => s1 + " " + s2).Trim();
if (text.Count < 7)
{
Info("Artifact id {0} is likely a photo or non-text image.", message.Id);
}
else
{
message.OCRText = text;
Info("OCR Text: {0}", alltext);
}
}
else
{
Info("No text recognized in artifact id {0}.", message.Id);
}
op.Complete();
}
message.Image.UnlockBits(bData);
if (text.Count >= 7)
{
TextArtifact artifact = new TextArtifact(message.Name + ".txt", text);
EnqueueMessage(artifact);
Info("{0} added artifact id {1} of type {2} from artifact {3}.", Name, artifact.Id, artifact.GetType(),
message.Id);
}
return(ApiResult.Success);
}
//public static void clearFaceFlag() { faceFlag = 0; }
public string RecognizeText(int id)
{
DBService dbs = new DBService();
Document doc = dbs.FindDocumentById(id);
Image <Gray, Byte> img = scale(doc);
//var image = PixConverter.ToPix(img.ToBitmap()))
Tesseract.Native.DllImports.TesseractDirectory = System.Web.HttpContext.Current.Server.MapPath("~/Tesseract/bin/Debug/DLLS/");
TessBaseAPI tessBaseAPI = new TessBaseAPI();
System.Diagnostics.Debug.WriteLine("The current version is {0}", tessBaseAPI.GetVersion());
string dataPath = System.Web.HttpContext.Current.Server.MapPath("~/tessdata/");
string language = "eng";
string inputFile = doc.Path;
OcrEngineMode oem = OcrEngineMode.DEFAULT;
//OcrEngineMode oem = OcrEngineMode.DEFAULT;
PageSegmentationMode psm = PageSegmentationMode.AUTO_OSD;
// Initialize tesseract-ocr
if (!tessBaseAPI.Init(dataPath, language, oem))
{
throw new Exception("Could not initialize tesseract.");
}
// Set the Page Segmentation mode
tessBaseAPI.SetPageSegMode(psm);
// Set the input image
Pix pix = tessBaseAPI.SetImage(inputFile);
// Recognize image
tessBaseAPI.Recognize();
ResultIterator resultIterator = tessBaseAPI.GetIterator();
// extract text from result iterator
StringBuilder stringBuilder = new StringBuilder();
int top, bottom, left, right, i = 0;
List <OCRText> forJson = new List <OCRText>();
PageIteratorLevel pageIteratorLevel = PageIteratorLevel.RIL_TEXTLINE;
do
{
string textContent = resultIterator.GetUTF8Text(pageIteratorLevel);
resultIterator.BoundingBox(pageIteratorLevel, out left, out top, out right, out bottom);
string coordsString = "" + left + "," + top + "," + right + "," + bottom;
forJson.Add(new OCRText()
{
Coords = coordsString, Text = textContent
});
} while (resultIterator.Next(pageIteratorLevel));
tessBaseAPI.Dispose();
pix.Dispose();
var textForReturn = JsonConvert.SerializeObject(forJson);
dbs.UpdateDocument(textForReturn, id);
if (HasFace(img) == true)
{
FaceFlag = 1;
}
else
{
FaceFlag = 0;
}
return(textForReturn);
}