/// <summary>
/// Gets an image resource by id
/// </summary>
/// <param name="id">Id to get</param>
/// <param name="imageType">Image type to get</param>
/// <param name="options">Options to use</param>
/// <returns>Handle to image resource if successful, otherwise <c>IntPtr.Zero</c></returns>
public IntPtr GetResource(int id, ImageType imageType, ImageLoadOptions options)
{
IntPtr handle = IntPtr.Zero;
if (!hLib.Equals(IntPtr.Zero))
{
handle = LoadImageLong(hLib, id, (int)imageType, 0, 0, (int)
options);
}
return(handle);
}
public static void Run()
{
string outputFolder = Constants.GetOutputDirectoryPath();
string outputFile = Path.Combine(outputFolder, "converted.pdf");
var imageLoadOptions = new ImageLoadOptions();
imageLoadOptions.SetOcrConnector(new OcrConnector());
using (Converter converter = new Converter(Constants.SAMPLE_JPEG, () => imageLoadOptions))
{
PdfConvertOptions options = new PdfConvertOptions();
converter.Convert(outputFile, options);
}
Console.WriteLine("\nDocument converted successfully. \nCheck output in {0}", outputFolder);
}
public FileImageSource(string path, ImageLoadOptions options) : base(options)
{
Path = Guard.NotNullOrEmpty(path, nameof(path));
}
/// <summary>
/// Recognize an image using Tesseract (free OCR library) and save the result as DOCX document.
/// </summary>
/// <remarks>
/// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/ocr-image-using-tesseract-and-save-as-docx-net-csharp-vb.php
/// </remarks>
static void RecognizeImage()
{
DocumentCore.Serial = "12345";
// Here we'll recognize an image (perform OCR) containing a text on English, Russian and Vietnamese.
// Next save the OCR result as a new DOCX document.
// First steps:
// 1. Download data files for English, Russian and Vietnamese languages.
// Please download the files: eng.traineddata, rus.traineddata and vie.traineddata.
// From here (good and fast): https://github.com/tesseract-ocr/tessdata_fast
// or (best and slow): https://github.com/tesseract-ocr/tessdata_best
// 2. Copy the files: eng.traineddata, rus.traineddata and vie.traineddata to
// the folder "tessdata" in the Project root.
// 3. Be sure that the folder "tessdata" also contains "pdf.ttf" file.
// Let's start:
string inpFile = @"..\..\image.png";
string outFile = "Result.docx";
ImageLoadOptions lo = new ImageLoadOptions();
lo.OCROptions.OCRMode = OCRMode.Enabled;
// You can specify all Tesseract parameters inside the method PerformOCR.
lo.OCROptions.Method = PerformOCRTesseract;
DocumentCore dc = DocumentCore.Load(inpFile, lo);
// Make all text visible after Tesseract OCR (change font color to Black).
// The matter is that Tesseract returns OCR result PDF document with invisible text.
// But with help of Document .Net, we can change the text color,
// char scaling and spacing to desired.
foreach (Run r in dc.GetChildElements(true, ElementType.Run))
{
r.CharacterFormat.FontColor = SautinSoft.Document.Color.Black;
r.CharacterFormat.Scaling = 100;
r.CharacterFormat.Spacing = 0;
r.CharacterFormat.Size = 12;
}
// Change the page size and add page margins.
Section section = dc.Sections[0];
section.PageSetup.PaperType = PaperType.Letter;
section.PageSetup.Orientation = Orientation.Landscape;
double m = LengthUnitConverter.Convert(5, LengthUnit.Millimeter, LengthUnit.Point);
section.PageSetup.PageMargins = new PageMargins()
{
Top = m, Left = m, Right = m, Bottom = m
};
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
public StreamImageSource(Stream stream, ImageLoadOptions options) : base(options)
{
Stream = Guard.NotNull(stream, nameof(stream));
}
public BufferImageSource(byte[] buffer, ImageLoadOptions options) : base(options)
{
Guard.NotNullOrEmpty(buffer, nameof(buffer));
Buffer = buffer;
}
/// <summary>
/// Gets an image resource by id
/// </summary>
/// <param name="id">Id to get</param>
/// <param name="imageType">Image type to get</param>
/// <param name="options">Options to use</param>
/// <returns>Handle to image resource if successful, otherwise <c>IntPtr.Zero</c></returns>
public IntPtr GetResource(int id, ImageType imageType, ImageLoadOptions options) {
IntPtr handle = IntPtr.Zero;
if (!hLib.Equals(IntPtr.Zero)) {
handle = LoadImageLong(hLib, id, (int)imageType, 0, 0, (int)
options);
}
return handle;
}
protected ImageSource(ImageLoadOptions options)
{
Options = options;
}
public VipsImageSource(Image image, ImageLoadOptions options) : base(options)
{
this.image = Guard.NotNull(image, nameof(image));
imageType = ImageType.FromImage(image);
}
