static void Main(string[] args)
{
string inputDocument = @".\areas-sample.pdf";
int pageIndex = 0;
string outputDocument = @".\result.txt";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputDocument);
// Set location of "tessdata" folder containing language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\tessdata\";
// Set OCR language.
// "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "tessdata" folder
// Find more language files at https://github.com/tesseract-ocr/tessdata/tree/3.04.00
textRecognizer.OCRLanguage = "eng";
// Get page size (in pixels). Size of PDF document is computed from PDF Points
// and the rendering resolution specified by `textRecognizer.PDFRenderingResolution` (default 300 DPI)
Size pageSize = textRecognizer.GetPageSize(pageIndex);
// Add area of interest as a rectangle at the top-right corner of the page
textRecognizer.RecognitionAreas.Add(pageSize.Width / 2, 0, pageSize.Width / 2, 300);
// Add area of interest as a rectangle at the bottom-left corner of the page,
// and indicate it should be rotated at 90 deg
textRecognizer.RecognitionAreas.Add(0, pageSize.Height / 2, 300, pageSize.Height / 2, AreaRotation.Rotate90FlipNone);
// Now, you can get recognized text for further analysis as a list of objects
// containing coordinates, object kind, confidence.
OCRObjectList ocrObjectList = textRecognizer.GetOCRObjects(pageIndex);
foreach (OCRObject ocrObject in ocrObjectList)
{
Console.WriteLine(ocrObject.ToString());
}
// ... or you can save recognized text pieces to file
textRecognizer.KeepTextFormatting = false; // save without formatting
textRecognizer.SaveText(outputDocument, pageIndex, pageIndex);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputDocument = @".\bad-quality.png";
string outputDocument = @".\result.txt";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputDocument);
// Set the location of OCR language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\ocrdata_fast\";
// Set OCR language.
// "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
textRecognizer.OCRLanguage = "eng";
// Add error corrections that will be applied after the recognition.
textRecognizer.Corrections.Add("Tut ", "Test ");
textRecognizer.Corrections.Add("Recog\\w{1,}on", "Recognition", true);
// Recognize text from all pages and save it to file
textRecognizer.SaveText(outputDocument);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string outputDocument = @".\result.txt";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Create ScreenshotMaker instance
ScreenshotMaker screenshotMaker = new ScreenshotMaker();
// Set rectangle to take screenshot from
screenshotMaker.SetScreenshotArea(0, 0, 200, 200);
// Load screenshot
textRecognizer.LoadDocument(screenshotMaker);
// Set the location of OCR language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\";
// Set OCR language.
// "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
textRecognizer.OCRLanguage = "eng";
// Recognize text from all pages and save it to file
textRecognizer.SaveText(outputDocument);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputUrl = @"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/image-to-pdf/image1.png";
string outputDocument = @".\result.txt";
// Get stream from input url
var inputStream = GetStreamFromUrl(inputUrl);
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputStream);
// Set the location of OCR language data files
textRecognizer.OCRLanguageDataFolder = @"C:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\";
// Set OCR language.
// "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
textRecognizer.OCRLanguage = "eng";
// Recognize text from all pages and save it to file
textRecognizer.SaveText(outputDocument);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputDocument = @".\ocr-sample.pdf";
string outputDocument = @".\result.json";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputDocument);
// Set the location of OCR language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\";
// Set OCR language.
// "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
textRecognizer.OCRLanguage = "eng";
// Recognize text from page and save each ocr word object to json
textRecognizer.SaveOCRObjectsAsJSON(outputDocument, 0, OCRObjectType.Word);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputDocument = @".\invoice-sample.png";
string outputDocument = @".\result.txt";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputDocument);
// Set location of "tessdata" folder containing language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\tessdata\";
// Set OCR language.
// "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "tessdata" folder
// Find more language files at https://github.com/tesseract-ocr/tessdata/tree/3.04.00
textRecognizer.OCRLanguage = "eng";
// Recognize text from all pages and save it to file
textRecognizer.SaveText(outputDocument);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputDocument = @".\skewed.png";
string outputDocument = @".\result.txt";
// Create and activate TextRecognizer instance
using (TextRecognizer textRecognizer = new TextRecognizer("demo", "demo"))
{
try
{
// Load document (image or PDF)
textRecognizer.LoadDocument(inputDocument);
// Set the location of OCR language data files
textRecognizer.OCRLanguageDataFolder = @"c:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\";
// Set OCR language.
// "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
textRecognizer.OCRLanguage = "eng";
// Add deskew filter that automatically rotates the image to make the text horizontal.
// Note, it analyzes the left edge of scanned text. Any dark artifacts may prevent
// the correct angle detection.
textRecognizer.ImagePreprocessingFilters.AddDeskew();
// Other filters that may be useful to improve recognition
// (note, the filters are applied in the order they were added):
// Improve image contrast.
//textRecognizer.ImagePreprocessingFilters.AddContrast();
// Apply gamma correction.
//textRecognizer.ImagePreprocessingFilters.AddGammaCorrection();
// Apply median filter. Helps to remove noise.
//textRecognizer.ImagePreprocessingFilters.AddMedian();
// Apply dilate filter. Helps to cure symbols erosion.
//textRecognizer.ImagePreprocessingFilters.AddDilate();
// Lines removers. Removing borders of some tables may improve the recognition.
//textRecognizer.ImagePreprocessingFilters.AddHorizontalLinesRemover();
//textRecognizer.ImagePreprocessingFilters.AddVerticalLinesRemover();
// Recognize text from all pages and save it to file
textRecognizer.SaveText(outputDocument);
// Open the result file in default associated application (for demo purposes)
Process.Start(outputDocument);
}
catch (Exception exception)
{
Console.WriteLine(exception);
}
}
// Console.WriteLine();
// Console.WriteLine("Press any key...");
// Console.ReadKey();
}
