Convert an Image to Grayscale PDF for Better OCR in C# or Java

using pdftron; 

using pdftron.Common; 

using pdftron.PDF; 

using pdftron.SDF; 

 

namespace ConsoleApp1 

{ 

    internal class Program 

    { 

        static void Main(string[] args) 

        { 

            try { 

 

                PDFNet.Initialize("your_license_key"); 

 

                string inputPath = "path_to_input_image"; 

                string exportGrayScalePath = "grayscale.jpg"; 

 

                PDFDoc doc = new PDFDoc(); 

                Page page = WritePage(doc, inputPath); 

                PDFDraw draw = new PDFDraw(300); 

                ObjSet hint_set = new ObjSet(); 

                Obj gray_hint = hint_set.CreateDict(); 

                gray_hint.PutName("ColorSpace", "Gray"); 

 

                draw.Export(page, exportGrayScalePath, "JPEG", gray_hint); 

 

                doc.Close(); 

 

                PDFDoc grayDoc = new PDFDoc(); 

                WritePage(grayDoc, exportGrayScalePath); 

 

                // Save the PDF 

                grayDoc.Save("grayscale.pdf", SDFDoc.SaveOptions.e_linearized); 

                grayDoc.Close(); 

 

                Console.WriteLine("Image converted to greyscale and added to PDF successfully!"); 

 

            } 

            catch (PDFNetException e) 

            { 

                Console.WriteLine(e.Message); 

            } 

 

        } 

 

        static Page WritePage(PDFDoc doc, string imageFile)  

        { 

 

            ElementBuilder builder = new ElementBuilder(); 

            ElementWriter writer = new ElementWriter(); 

            Image img = Image.Create(doc, imageFile); 

            Page page = doc.PageCreate(new Rect(0, 0, img.GetImageWidth(), img.GetImageHeight())); 

            writer.Begin(page); 

            Element element = builder.CreateImage(img, 0, 0, img.GetImageWidth(), img.GetImageHeight()); 

            writer.WritePlacedElement(element); 

            writer.End(); 

            doc.PagePushBack(page); 

 

            return page; 

        } 

    } 

} 

import com.pdftron.common.PDFNetException; 

import com.pdftron.pdf.*; 

import com.pdftron.sdf.*; 

 

public class App { 

public static void main(String[] args) { 

  try { 

    PDFNet.initialize("your_license_key"); 

 

    String inputPath = "path_to_input_image"; 

    String exportGrayScalePath = "src\\samples\\grayscale.jpg"; 

 

    PDFDoc doc = new PDFDoc(); 

    Page page = writePage(doc, inputPath); 

    PDFDraw draw = new PDFDraw(); 

    draw.setDPI(300); 

    ObjSet hintSet = new ObjSet(); 

    Obj grayHint = hintSet.createDict(); 

    grayHint.putName("ColorSpace", "Gray"); 

 

    draw.export(page, exportGrayScalePath, "JPEG", grayHint); 

 

    doc.close(); 

 

    PDFDoc grayDoc = new PDFDoc(); 

    writePage(grayDoc, exportGrayScalePath); 

 

    // Save the PDF 

    grayDoc.save("src\\samples\\grayscale.pdf", SDFDoc.SaveMode.LINEARIZED, null); 

    grayDoc.close(); 

 

    System.out.println("Image converted to grayscale and added to PDF successfully!"); 

 

  } catch (PDFNetException e) { 

    System.out.println(e.getMessage()); 

  } 

  } 

 

  static Page writePage(PDFDoc doc, String imageFile) throws PDFNetException { 

    ElementBuilder builder = new ElementBuilder(); 

    ElementWriter writer = new ElementWriter(); 

    Image img = Image.create(doc, imageFile); 

    Page page = doc.pageCreate(new Rect(0, 0, img.getImageWidth(), img.getImageHeight())); 

    writer.begin(page); 

    Element element = builder.createImage(img, 0, 0, img.getImageWidth(), img.getImageHeight()); 

    writer.writePlacedElement(element); 

    writer.end(); 

    doc.pagePushBack(page); 

 

    return page; 

  } 

}