Hi Everyone
I'm very new here. I wonder how I can raise the image quality in pdf?? what 
can I do for this, here is an example file)
I try to keep the quality at 300 dpi and throw it into the PIX class.
here is my sample code. outputs 0.52% when reading. I would like to raise 
it to 80-85%






















































*var documentText = new StringBuilder();            using (var pdf = new 
PdfDocument("chet6.pdf"))            {                using (var engine = 
new TesseractEngine(@"tessdata", "rus+eng", EngineMode.LstmOnly))          
      {                    for (int i = 0; i < pdf.PageCount; ++i)          
          {                        if (documentText.Length > 0)            
                documentText.Append("\r\n\r\n");                        
PdfPage page = pdf.Pages[i];                        string searchableText = 
page.GetText();                        // Simple check if the page contains 
searchable text.                        // We do not need to perform OCR in 
that case.                        //foreach (PdfImage image in 
page.GetImages())                        //{                        //   
 // simple hack to replace the right-bottom image only                      
  //    if (image.Height == 512)                        //       
 image.ReplaceWith("1px.png");                        //}                  
      if (!string.IsNullOrEmpty(searchableText.Trim()))                    
    {                            documentText.Append(searchableText);      
                      continue;                        }                    
    // Save PDF page as high-resolution image                        
PdfDrawOptions options = PdfDrawOptions.Create();                        
options.BackgroundColor = new PdfRgbColor(255, 255, 255);                  
      options.HorizontalResolution = 300;                        
options.VerticalResolution = 300;                        string pageImage = 
$"page_{i}.png";                        page.Save(pageImage, options);      
                  //page.Rotation = PdfRotation.None;                      
  //page.Save(pageImage, options);                        // Perform OCR    
                    using (Pix img = Pix.LoadFromFile(pageImage))          
              {                            //using (Page recognizedPage = 
engine.Process(img, PageSegMode.SingleBlock))                            
using (Page recognizedPage = engine.Process(img))                          
  {                                Console.WriteLine($"Mean confidence for 
page #{i}: {recognizedPage.GetMeanConfidence()}");                          
      string recognizedText = recognizedPage.GetText();                    
            documentText.Append(recognizedText);                            
}                        }                        File.Delete(pageImage);  
                  }                }            }            using (var 
writer = new StreamWriter("result.txt"))                
writer.Write(documentText.ToString());        }*

-- 
You received this message because you are subscribed to the Google Groups 
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/44e20de8-6ca3-4a0a-a797-f37aa672b09en%40googlegroups.com.

Attachment: chet6.pdf
Description: Adobe PDF document

Reply via email to