//This function will find every image in the document and add text if
//possible
static void AddTextToImages(Document doc, Content content, OCREngine engine)
{
for (int index = 0; index < content.NumElements; index++)
{
Element e = content.GetElement(index);
if (e is Datalogics.PDFL.Image)
{
//PlaceTextUnder creates a form with the image and the generated text
//under the image. The original image in the page is then replaced by
//by the form.
Form form = engine.PlaceTextUnder((Image)e, doc);
content.RemoveElement(index);
content.AddElement(form, index - 1);
}
else if (e is Container)
{
AddTextToImages(doc, (e as Container).Content, engine);
}
else if (e is Group)
{
AddTextToImages(doc, (e as Group).Content, engine);
}
else if (e is Form)
{
AddTextToImages(doc, (e as Form).Content, engine);
}
}
}
static void Main(string[] args)
{
Console.WriteLine("AddTextToDocument Sample:");
// ReSharper disable once UnusedVariable
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/scanned_images.pdf";
String sOutput = "AddTextToDocument-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Console.WriteLine("Input file: " + sInput);
Console.WriteLine("Writing output to: " + sOutput);
OCRParams ocrParams = new OCRParams();
//The OCRParams.Languages parameter controls which languages the OCR engine attempts
//to detect. By default the OCR engine searches for English.
List <LanguageSetting> langList = new List <LanguageSetting>();
LanguageSetting languageOne = new LanguageSetting(Language.English, false);
langList.Add(languageOne);
//You could add additional languages for the OCR engine to detect by adding
//more entries to the LanguageSetting list.
//LanguageSetting languageTwo = new LanguageSetting(Language.Japanese, false);
//langList.Add(languageTwo);
ocrParams.Languages = langList;
using (OCREngine ocrEngine = new OCREngine(ocrParams))
{
//Create a document object using the input file
using (Document doc = new Document(sInput))
{
for (int numPage = 0; numPage < doc.NumPages; numPage++)
{
using (Page page = doc.GetPage(numPage))
{
Content content = page.Content;
Console.WriteLine("Adding text to page: " + numPage);
AddTextToImages(doc, content, ocrEngine);
page.UpdateContent();
}
}
doc.Save(SaveFlags.Full, sOutput);
}
}
}
}
static void Main(string[] args)
{
Console.WriteLine("AddTextToDocument Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/scanned_images.pdf";
String sOutput = "../AddTextToDocument-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Console.WriteLine("Input file: " + sInput);
Console.WriteLine("Writing output to: " + sOutput);
OCRParams ocrParams = new OCRParams();
// Setting the segmentation mode to AUTOMATIC lets the OCR engine
// choose how to segment the page for text detection.
ocrParams.PageSegmentationMode = PageSegmentationMode.Automatic;
// This tells the selected engine to improve accuracy at the expense
// of increased run time. For Tesseract 3, it runs two different
// algorithms, and chooses the one that has the most confidence.
ocrParams.Performance = Performance.BestAccuracy;
using (OCREngine ocrEngine = new OCREngine(ocrParams))
{
//Create a document object using the input file
using (Document doc = new Document(sInput))
{
for (int numPage = 0; numPage < doc.NumPages; numPage++)
{
using (Page page = doc.GetPage(numPage))
{
Content content = page.Content;
Console.WriteLine("Adding text to page: " + numPage);
AddTextToImages(doc, content, ocrEngine);
page.UpdateContent();
}
}
doc.Save(SaveFlags.Full, sOutput);
}
}
}
}
public ComicTransMainWindow()
{
InitializeComponent();
TransResListView.ItemsSource = lstData;
ComicImgList = new List <string>();
CurrentPos = 0;
transRes1 = "";
transRes2 = "";
_translator1 = TranslateWindow.TranslatorAuto(Common.appSettings.FirstTranslator);
_translator2 = TranslateWindow.TranslatorAuto(Common.appSettings.SecondTranslator);
ocr = OCRCommon.OCRAuto(Common.appSettings.OCRsource);
ocr.SetOCRSourceLang("jpn");
if (Common.appSettings.OCRsource == "BaiduOCR")
{
if (ocr.OCR_Init(Common.appSettings.BDOCR_APIKEY, Common.appSettings.BDOCR_SecretKey) == false)
{
HandyControl.Controls.Growl.ErrorGlobal($"百度OCR {Application.Current.Resources["APITest_Error_Hint"]}\n{ocr.GetLastError()}");
}
}
else if (Common.appSettings.OCRsource == "Tesseract5")
{
if (ocr.OCR_Init(Common.appSettings.Tesseract5OCR_Path, Common.appSettings.Tesseract5OCR_Args) == false)
{
HandyControl.Controls.Growl.ErrorGlobal($"Tesseract5 {Application.Current.Resources["APITest_Error_Hint"]}\n{ocr.GetLastError()}");
}
}
else if (Common.appSettings.OCRsource == "TesseractOCR")
{
if (ocr.OCR_Init("", "") == false)
{
HandyControl.Controls.Growl.ErrorGlobal($"TesseractOCR {Application.Current.Resources["APITest_Error_Hint"]}\n{ocr.GetLastError()}");
}
}
scale = Common.GetScale();
DrawingAttributes drawingAttributes = new DrawingAttributes
{
Color = Colors.Red,
Width = 2,
Height = 2,
StylusTip = StylusTip.Rectangle,
//FitToCurve = true,
IsHighlighter = false,
IgnorePressure = true,
};
inkCanvasMeasure.DefaultDrawingAttributes = drawingAttributes;
viewModel = new ViewModel
{
MeaInfo = "",
InkStrokes = new StrokeCollection(),
};
DataContext = viewModel;
}
static void Main(string[] args)
{
Console.WriteLine("AddTextToImage Sample:");
// ReSharper disable once UnusedVariable
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/text_as_image.jpg";
String sOutput = "AddTextToImage-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Console.WriteLine("Input file: " + sInput);
Console.WriteLine("Writing output to: " + sOutput);
OCRParams ocrParams = new OCRParams();
//The OCRParams.Languages parameter controls which languages the OCR engine attempts
//to detect. By default the OCR engine searches for English.
List <LanguageSetting> langList = new List <LanguageSetting>();
LanguageSetting languageOne = new LanguageSetting(Language.English, false);
langList.Add(languageOne);
//You could add additional languages for the OCR engine to detect by adding
//more entries to the LanguageSetting list.
//LanguageSetting languageTwo = new LanguageSetting(Language.Japanese, false);
//langList.Add(languageTwo);
ocrParams.Languages = langList;
// If your image resolution is not 300 dpi, specify it here. Specifying a
// correct resolution gives better results for OCR, especially with
// automatic image preprocessing.
// ocrParams.Resolution = 600;
using (OCREngine ocrEngine = new OCREngine(ocrParams))
{
//Create a document object
using (Document doc = new Document())
{
using (Image newimage = new Image(sInput, doc))
{
// Create a PDF page which is the size of the image.
// Matrix.A and Matrix.D fields, respectively.
// There are 72 PDF user space units in one inch.
Rect pageRect = new Rect(0, 0, newimage.Matrix.A, newimage.Matrix.D);
using (Page docpage = doc.CreatePage(Document.BeforeFirstPage, pageRect))
{
docpage.Content.AddElement(newimage);
docpage.UpdateContent();
}
}
using (Page page = doc.GetPage(0))
{
Content content = page.Content;
Element elem = content.GetElement(0);
Image image = (Image)elem;
//PlaceTextUnder creates a form with the image and the generated text
//under the image. The original image in the page is then replaced by
//by the form.
Form form = ocrEngine.PlaceTextUnder(image, doc);
content.RemoveElement(0);
content.AddElement(form, Content.BeforeFirst);
page.UpdateContent();
}
doc.Save(SaveFlags.Full, sOutput);
}
}
}
}
static void Main(string[] args)
{
Console.WriteLine("AddTextToImage Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/text_as_image.jpg";
String sOutput = "../AddTextToImage-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Console.WriteLine("Input file: " + sInput);
Console.WriteLine("Writing output to: " + sOutput);
OCRParams ocrParams = new OCRParams();
// Setting the segmentation mode to AUTOMATIC lets the OCR engine
// choose how to segment the page for text detection.
ocrParams.PageSegmentationMode = PageSegmentationMode.Automatic;
// This tells the selected engine to improve accuracy at the expense
// of increased run time. For Tesseract 3, it runs two different
// algorithms, and chooses the one that has the most confidence.
ocrParams.Performance = Performance.BestAccuracy;
using (OCREngine ocrEngine = new OCREngine(ocrParams))
{
//Create a document object
using (Document doc = new Document())
{
using (Image newimage = new Image(sInput, doc))
{
// Create a PDF page which is the size of the image.
// Matrix.A and Matrix.D fields, respectively.
// There are 72 PDF user space units in one inch.
Rect pageRect = new Rect(0, 0, newimage.Matrix.A, newimage.Matrix.D);
using (Page docpage = doc.CreatePage(Document.BeforeFirstPage, pageRect))
{
docpage.Content.AddElement(newimage);
docpage.UpdateContent();
}
}
using (Page page = doc.GetPage(0))
{
Content content = page.Content;
Element elem = content.GetElement(0);
Image image = (Image)elem;
//PlaceTextUnder creates a form with the image and the generated text
//under the image. The original image in the page is then replaced by
//by the form.
Form form = ocrEngine.PlaceTextUnder(image, doc);
content.RemoveElement(0);
content.AddElement(form, -1);
page.UpdateContent();
}
doc.Save(SaveFlags.Full, sOutput);
}
}
}
}
static void Main(string[] args)
{
Console.WriteLine("AddTextToDocument Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/scanned_images.pdf";
String sOutput = "../AddTextToDocument-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Console.WriteLine("Input file: " + sInput);
Console.WriteLine("Writing output to: " + sOutput);
OCRParams ocrParams = new OCRParams();
using (Document doc = new Document(sInput))
{
var segmodeList = new List <PageSegmentationMode>();
var performanceOpt = new List <Datalogics.PDFL.Performance>();
performanceOpt.Add(Datalogics.PDFL.Performance.Default);
performanceOpt.Add(Datalogics.PDFL.Performance.Faster);
performanceOpt.Add(Datalogics.PDFL.Performance.MoreAccuracy);
performanceOpt.Add(Datalogics.PDFL.Performance.BestAccuracy);
int index = 0;
foreach (Datalogics.PDFL.Performance perfOpt in performanceOpt)
{
ocrParams.PageSegmentationMode = PageSegmentationMode.Automatic;
ocrParams.Performance = perfOpt;
Console.WriteLine("\nUsing Performance option " + perfOpt.ToString() + " and PageSegmentationMode.Automatic");
var sw = Stopwatch.StartNew();
using (OCREngine ocrEngine = new OCREngine(ocrParams))
{
for (int numPage = 0; numPage < doc.NumPages; numPage++)
{
using (Page page = doc.GetPage(numPage))
{
Content content = page.Content;
sw = Stopwatch.StartNew();
AddTextToImages(doc, content, ocrEngine);
//page.UpdateContent();
sw.Stop();
TimeSpan timeElapsed = sw.Elapsed;
Console.WriteLine(" Page " + numPage + " -- Time elapsed: " + timeElapsed.TotalMilliseconds + " milliseconds");
}
}
index++;
//doc.Save(SaveFlags.Full, sOutput);
}
}
/*
* ocrParams.PageSegmentationMode = PageSegmentationMode.Automatic;
* ocrParams.Performance = Performance.MoreAccuracy;
* sw = Stopwatch.StartNew();
* using (OCREngine ocrEngine = new OCREngine(ocrParams))
* {
* for (int numPage = 0; numPage < doc.NumPages; numPage++)
* {
* using (Page page = doc.GetPage(numPage))
* {
* Content content = page.Content;
* sw = Stopwatch.StartNew();
* AddTextToImages(doc, content, ocrEngine);
* //page.UpdateContent();
* sw.Stop();
* TimeSpan timeElapsed = sw.Elapsed;
* Console.WriteLine("\nUsing Performance.MoreAccuracy and PageSegmentationMode.Automatic");
* Console.WriteLine(" Page " + numPage + " -- Time elapsed: " + timeElapsed.TotalMilliseconds + " milliseconds");
*
* }
* }
* //doc.Save(SaveFlags.Full, sOutput);
* }
*
* ocrParams.PageSegmentationMode = PageSegmentationMode.Automatic;
* ocrParams.Performance = Performance.BestAccuracy;
* sw = Stopwatch.StartNew();
* using (OCREngine ocrEngine = new OCREngine(ocrParams))
* {
* for (int numPage = 0; numPage < doc.NumPages; numPage++)
* {
* using (Page page = doc.GetPage(numPage))
* {
* Content content = page.Content;
* sw = Stopwatch.StartNew();
* AddTextToImages(doc, content, ocrEngine);
* //page.UpdateContent();
* sw.Stop();
* TimeSpan timeElapsed = sw.Elapsed;
* Console.WriteLine("\nUsing Performance.BestAccuracy and PageSegmentationMode.Automatic");
* Console.WriteLine(" Page " + numPage + " -- Time elapsed: " + timeElapsed.TotalMilliseconds + " milliseconds");
*
* }
* }
* //doc.Save(SaveFlags.Full, sOutput);
* }
*/
}
}
}
