/// <summary>
/// Get Image Contents
/// </summary>
private static string _GetImageContet(FileInfo fileInfo)
{
//Read all file content...
using (TextExtractor extractor = new TextExtractor())
{
// Load document
extractor.LoadDocumentFromFile(fileInfo.FullName);
//Set option to repair text
extractor.OCRMode = OCRMode.TextFromImagesAndVectorsAndRepairedFonts;
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
extractor.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
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// Read all text
return(extractor.GetText());
}
}
private void btnGetData_Click(object sender, EventArgs e)
{
StringBuilder result = new StringBuilder();
RectangleF[] selection = pdfViewerControl1.SelectionInPoints;
using (TextExtractor extractor = new TextExtractor())
{
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
extractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
extractor.OCRMode = OCRMode.Auto;
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
extractor.OCRResolution = 300;
for (int i = 0; i < selection.Length; i++)
{
extractor.SetExtractionArea(selection[i]);
result.AppendLine(_dataLabels[i]);
result.AppendLine(extractor.GetText(pdfViewerControl1.CurrentPageIndex, pdfViewerControl1.CurrentPageIndex));
result.AppendLine();
}
}
MessageBox.Show(result.ToString());
}
/// <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)
{
String inputFile = Server.MapPath(@".\bin\sample_ocr.pdf");
// Location of language files
String ocrLanguageDataFolder = Server.MapPath(@".\tessdata");
// Create Bytescout.PDFExtractor.TextExtractor instance
using (TextExtractor extractor = new TextExtractor())
{
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of "tessdata" folder containing language data file
extractor.OCRLanguageDataFolder = ocrLanguageDataFolder;
// Set OCR language
extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in /tessdata
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
// Automatically deskew skewed scans
//extractor.OCRImagePreprocessingFilters.AddDeskew();
// Repair broken letters
//extractor.OCRImagePreprocessingFilters.AddDilate();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentations errors)
//extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover();
//extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Remove noise
//extractor.OCRImagePreprocessingFilters.AddMedian();
// Apply Gamma Correction
//extractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// Load PDF document
extractor.LoadDocumentFromFile(inputFile);
// Write extracted text to output stream
Response.Clear();
Response.ContentType = "text/html";
Response.Write("<pre>");
// Write extracted text to output stream
Response.Write(extractor.GetText());
Response.Write("</pre>");
Response.End();
}
}
private void Button_Extract(object sender, RoutedEventArgs e)
{
if (_pdfFile != null)
{
string text = extractor.GetText(0, 0); // extract from the first page only (for demonstration purposes)
textBox1.Text = text;
}
}
/// <summary>
/// Get PDF File Content
/// </summary>
private static string _GetPdfFileContent(FileInfo fileInfo)
{
//Read all file content...
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
//Load Document
textExtractor.LoadDocumentFromFile(fileInfo.FullName);
return(textExtractor.GetText());
}
}
static void Main(string[] args)
{
try
{
//Read all file content...
using (TextExtractor extractor = new TextExtractor())
{
// Load document
extractor.LoadDocumentFromFile("sample.png");
// Extractor Progress event
Console.WriteLine("Text Extraction in progress: \n");
extractor.ProgressChanged += Extractor_ProgressChanged;
// Set option to repair text
extractor.OCRMode = OCRMode.TextFromImagesAndVectorsAndRepairedFonts;
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";
// Set OCR language
extractor.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
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
//Read all text
var allExtractedText = extractor.GetText();
Console.WriteLine("\n\nExtracted Text:\n\n{0}", allExtractedText);
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
Console.WriteLine("Press enter key to exit...");
Console.ReadLine();
}
/// <summary>
/// Check whether OCR Operation is required
/// </summary>
/// <param name="filePath"></param>
private static void _CheckOCRRequired(string filePath)
{
//Read all file content...
using (TextExtractor extractor = new TextExtractor())
{
extractor.RegistrationKey = "demo";
extractor.RegistrationName = "demo";
// Load document
extractor.LoadDocumentFromFile(filePath);
Console.WriteLine("\n*******************\n\nFilePath: {0}", filePath);
int pageIndex = 0;
// Identify OCR operation is recommended for page
if (extractor.IsOCRRecommendedForPage(pageIndex))
{
Console.WriteLine("\nOCR Recommended: True");
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
extractor.OCRMode = OCRMode.Auto;
// Set the location of language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";
// Set OCR language
extractor.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
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
}
else
{
Console.WriteLine("\nOCR Recommended: False");
}
//Read all text
var allExtractedText = extractor.GetText();
Console.WriteLine("\nExtracted Text:\n{0}\n\n", allExtractedText);
}
}
static void Main(string[] args)
{
try
{
//Read all text from pdf file
using (TextExtractor extractor = new TextExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile("sample.pdf");
// Set the font repairing OCR mode
extractor.OCRMode = OCRMode.TextFromImagesAndVectorsAndRepairedFonts;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata\";
// Set OCR language
extractor.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
// Set PDF document rendering resolution
extractor.OCRResolution = 300;
//Read all text
string allText = extractor.GetText();
Console.WriteLine("Extracted Text: \n\n" + allText);
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
Console.ReadLine();
}
static void Main(string[] args)
{
try
{
// Files
string fileName = "hindi_text_with_image.pdf";
string destFileName = "output_hindi_text_with_image.pdf";
string destFileName_serachable = "output_hindi_text_with_image_searchable.pdf";
// Read all text from pdf file
string allTextExtracted = "";
using (TextExtractor extractor = new TextExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile(fileName);
// Read all text directly
allTextExtracted = extractor.GetText();
}
// Get image from pdf file
MemoryStream memoryStream = new MemoryStream();
using (ImageExtractor extractor = new ImageExtractor())
{
// Load PDF document
extractor.LoadDocumentFromFile(fileName);
if (extractor.GetFirstImage())
{
extractor.SaveCurrentImageToStream(memoryStream, ImageFormat.Png);
}
}
// Load image from file to System.Drawing.Image object (we need it to get the image resolution)
using (System.Drawing.Image sysImage = System.Drawing.Image.FromStream(memoryStream))
{
// Compute image size in PDF units (Points)
float widthInPoints = sysImage.Width / sysImage.HorizontalResolution * 72f;
float heightInPoints = sysImage.Height / sysImage.VerticalResolution * 72f;
// Create new PDF document
using (Document outPdfDocument = new Document())
{
outPdfDocument.RegistrationName = "demo";
outPdfDocument.RegistrationKey = "demo";
// Create page of computed size
Page page = new Page(widthInPoints, heightInPoints);
// Add page to the document
outPdfDocument.Pages.Add(page);
Canvas canvas = page.Canvas;
// Create Bytescout.PDF.Image object from loaded image
Image pdfImage = new Image(sysImage);
// Draw the image
canvas.DrawImage(pdfImage, 0, 0, widthInPoints, heightInPoints);
// Dispose the System.Drawing.Image object to free resources
sysImage.Dispose();
// Create brush
SolidBrush transparentBrush = new SolidBrush(new ColorGray(0));
// ... and make it transparent
transparentBrush.Opacity = 0;
// Draw text with transparent brush
// Need to set Font which supports hindi characters.
Font font16 = new Font("Arial Unicode MS", 16);
canvas.DrawString(allTextExtracted, font16, transparentBrush, 40, 40);
// Save document to file
outPdfDocument.Save(destFileName);
}
}
// Make PDF file with hindi text searchable to OCR.
using (SearchablePDFMaker searchablePDFMaker = new SearchablePDFMaker())
{
//Load PDF document
searchablePDFMaker.LoadDocumentFromFile(destFileName);
// Set the location of "tessdata" folder containing language data files
/*
* It used following files for hindi language support. Need to put these files into "testdata" folder. Below location contains these files.
* https://github.com/tesseract-ocr/tessdata/tree/3.04.00
* hin.traineddata
* hin.cube.bigrams
* hin.cube.lm
* hin.cube.nn
* hin.cube.params
* hin.cube.word-freq
* hin.tesseract_cube.nn
*/
searchablePDFMaker.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\Redistributable\net2.00\tessdata\";
// Set OCR language
searchablePDFMaker.OCRLanguage = "hin";
// Need to set Font which supports hindi characters
searchablePDFMaker.LabelingFont = "Arial Unicode MS";
// Set PDF document rendering resolution
searchablePDFMaker.OCRResolution = 300;
searchablePDFMaker.MakePDFSearchable(destFileName_serachable);
}
// Open document in default PDF viewer app
Process.Start(destFileName_serachable);
}
catch (Exception ex)
{
Console.WriteLine("ERROR:" + ex.Message);
}
Console.ReadLine();
}
static void Main(string[] args)
{
try
{
//Read all text from noisy image file
using (TextExtractor extractor = new TextExtractor())
{
// Load noisy image document
extractor.LoadDocumentFromFile("sample.png");
// Set the font repairing OCR mode
extractor.OCRMode = OCRMode.TextFromImagesAndVectorsAndRepairedFonts;
// Set the location of OCR language data files
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
// Set OCR language
extractor.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
// Set document rendering resolution
extractor.OCRResolution = 300;
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
Console.WriteLine("Please wait while PDF Extractor SDK is processing noisy image to read data...");
// Automatically deskew skewed scans
extractor.OCRImagePreprocessingFilters.AddDeskew();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentation errors)
//extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover();
//extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Repair broken letters
extractor.OCRImagePreprocessingFilters.AddDilate();
// Remove noise
extractor.OCRImagePreprocessingFilters.AddMedian();
// Apply Gamma Correction
extractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// Add Contrast
//extractor.OCRImagePreprocessingFilters.AddContrast(20);
// (!) You can use new OCRAnalyser class to find an optimal set of image preprocessing
// filters for your specific document.
// See "OCR Analyser" example.
//Read all text
string allText = extractor.GetText();
Console.Clear();
Console.WriteLine("Extracted Text: \n\n" + allText);
}
}
catch (Exception ex)
{
Console.Clear();
Console.WriteLine("Exception: " + ex.Message);
}
Console.ReadLine();
}
