The Apryse Fall 2026 release is here!
Ctrlk
QuickstartContact SalesSign In
For the complete documentation index, see llms.txt. This page is also available as Markdown.
Extraction

OCR - search PDFs and Extract Text

Requirements

These packages are required to use these features in production. Trial keys have unlimited access to all features

Server SDKPackage: OCRModule: OCRLive demo

Sample code shows how to use the Apryse Server OCR module on scanned documents in multiple languages; provided in Python, C++, C# (.Net), Java, Node.js (JavaScript), PHP, Ruby and VB. The OCR module can make searchable PDFs and extract scanned text for further indexing.

Looking for OCR + WebViewer? Check out our OCR - Showcase Sample Code

Learn more about our Server SDK and OCR capabilities.

Implementation steps

To run this sample, you will need:

  1. Get started with Server SDK in your language/framework

  2. Download OCR Module

  3. Add the sample code provided below

To use this feature in production, your license key will need the OCR Package. Trial keys already include this package.

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2024 by Apryse Software Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.     
//---------------------------------------------------------------------------------------

using System;
using pdftron;
using pdftron.Common;
using pdftron.SDF;
using pdftron.PDF;

namespace OCRTestCS
{
    
    /// <summary>
    //---------------------------------------------------------------------------------------
    // The following sample illustrates how to use OCR module
    //---------------------------------------------------------------------------------------
    /// </summary>
    class Class1
    {
        private static pdftron.PDFNetLoader pdfNetLoader = pdftron.PDFNetLoader.Instance();
        static Class1() {}
        
        /// <summary>
        /// The main entry point for the application.
        /// </summary>
        static void Main(string[] args)
        {
            // The first step in every application using PDFNet is to initialize the 
            // library and set the path to common PDF resources. The library is usually 
            // initialized only once, but calling Initialize() multiple times is also fine.
            PDFNet.Initialize(PDFTronLicense.Key);

            // Can optionally set path to the OCR module
            PDFNet.AddResourceSearchPath("../../../../../Lib/");

            // if the IRIS OCR module is available, will use that instead of the default
            bool use_iris = OCRModule.IsIRISModuleAvailable();
            if( !OCRModule.IsModuleAvailable() )
            {
                Console.WriteLine("");
                Console.WriteLine("Unable to run OCRTest: Apryse SDK OCR module not available.");
                Console.WriteLine("---------------------------------------------------------------");
                Console.WriteLine("The OCR module is an optional add-on, available for download");
                Console.WriteLine("at https://docs.apryse.com/core/guides/info/modules#ocr-module . If you have already downloaded this");
                Console.WriteLine("module, ensure that the SDK is able to find the required files");
                Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
                Console.WriteLine("");
                return;
            }

            // Relative path to the folder containing test files.
            string input_path =  "../../../../TestFiles/OCR/";
            string output_path = "../../../../TestFiles/Output/";

            //--------------------------------------------------------------------------------
            // Example 1) Process image
            try
            {

                // A) Setup empty destination doc
                using (PDFDoc doc = new PDFDoc())
                {
                    // B) Set English as the language of choice
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("eng");

                    // C) Run OCR on the .png with options            
                    OCRModule.ImageToPDF(doc, input_path + "psychomachia_excerpt.png", opts);

                    // D) check the result
                    doc.Save(output_path + "psychomachia_excerpt.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 1: psychomachia_excerpt.png");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 2) Process document using multiple languages
            try
            {

                // A) Setup empty destination doc
                using (PDFDoc doc = new PDFDoc())
                {

                    // B) Setup options with multiple target languages, English will always be considered as secondary language
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("deu");
                    opts.AddLang("fra");
                    opts.AddLang("eng");

                    // C) Run OCR on the .jpg with options        
                    OCRModule.ImageToPDF(doc, input_path + "multi_lang.jpg", opts);

                    // D) check the result
                    doc.Save(output_path + "multi_lang.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 2: multi_lang.jpg");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 3) Process a .pdf specifying a language - German - and ignore zone comprising a sidebar image 
            try
            {

                // A) Open the .pdf document
                using (PDFDoc doc = new PDFDoc(input_path + "german_kids_song.pdf"))
                {

                    // B) Setup options with a single language and an ignore zone
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("deu");

                    RectCollection ignoreZones = new RectCollection();
                    ignoreZones.AddRect(424, 163, 493, 730);
                    opts.AddIgnoreZonesForPage(ignoreZones, 1);

                    // C) Run OCR on the .pdf with options
                    OCRModule.ProcessPDF(doc, opts);

                    // D) check the result
                    doc.Save(output_path + "german_kids_song.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 3: german_kids_song.pdf");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 4) Process multipage tiff with text/ignore zones specified for each page
            try
            {

                // A) Setup empty destination doc
                using (PDFDoc doc = new PDFDoc())
                {

                    // B) Setup options with a single language plus text/ignore zones
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("eng");

                    RectCollection zones = new RectCollection();


                    // ignore signature box in the first 2 pages
                    zones.AddRect(1492, 56, 2236, 432);
                    opts.AddIgnoreZonesForPage(zones, 1);
                    zones.Clear();

                    zones.AddRect(1492, 56, 2236, 432);
                    opts.AddIgnoreZonesForPage(zones, 2);
                    zones.Clear();

                    // can use a combination of ignore and text boxes to focus on the page area of interest,
                    // as ignore boxes are applied first, we remove the arrows before selecting part of the diagram
                    zones.AddRect(992, 1276, 1368, 1372);
                    opts.AddIgnoreZonesForPage(zones, 3);
                    zones.Clear();

                    // select horizontal BUFFER ZONE sign
                    zones.AddRect(900, 2384, 1236, 2480);
                    // select right vertical BUFFER ZONE sign
                    zones.AddRect(1960, 1976, 2016, 2296);
                    // select Lot No.
                    zones.AddRect(696, 1028, 1196, 1128);

                    // select part of the plan inside the BUFFER ZONE
                    zones.AddRect(428, 1484, 1784, 2344);
                    zones.AddRect(948, 1288, 1672, 1476);
                    opts.AddTextZonesForPage(zones, 3);

                    // C) Run OCR on the .pdf with options
                    OCRModule.ImageToPDF(doc, input_path + "bc_environment_protection.tif", opts);

                    // D) check the result
                    doc.Save(output_path + "bc_environment_protection.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 4: bc_environment_protection.tif");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 5) Alternative workflow for extracting OCR result JSON, postprocessing (e.g., removing words not in the dictionary or filtering special
            // out special characters), and finally applying modified OCR JSON to the source PDF document 
            try
            {

                // A) Open the .pdf document
                using (PDFDoc doc = new PDFDoc(input_path + "zero_value_test_no_text.pdf"))
                {

                    // B) set English language
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("eng");


                    // C) Run OCR on the .pdf 
                    string json = OCRModule.GetOCRJsonFromPDF(doc, opts);

                    // D) Post-processing step (whatever it might be), but we just print JSON here
                    Console.WriteLine("Have OCR result JSON, re-applying to PDF");

                    // E) Apply potentially modified OCR JSON to the PDF
                    OCRModule.ApplyOCRJsonToPDF(doc, json);

                    // F) check the result
                    doc.Save(output_path + "zero_value_test_no_text.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 5: extracting and applying OCR JSON from zero_value_test_no_text.pdf");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 6) The postprocessing workflow has also an option of extracting OCR results in XML format, similar to the one used by TextExtractor
            try
            {

                // A) Setup empty destination doc
                using (PDFDoc doc = new PDFDoc())
                {

                    // B) set English language
                    OCROptions opts = new OCROptions();
                    if(use_iris) opts.SetOCREngine("iris");
                    opts.AddLang("eng");

                    // C) Run OCR on the .tif with default English language, extracting OCR results in XML format. Note that
                    // in the process we convert the source image into PDF. We reuse this PDF document later to add hidden text layer to it.

                    string xml = OCRModule.GetOCRXmlFromImage(doc, input_path + "physics.tif", opts);

                    // D) Post-processing step (whatever it might be), but we just print XML here
                    Console.WriteLine("Have OCR result XML, re-applying to PDF");

                    // E) Apply potentially modified OCR XML to the PDF
                    OCRModule.ApplyOCRXmlToPDF(doc, xml);

                    // F) check the result
                    doc.Save(output_path + "physics.pdf", SDFDoc.SaveOptions.e_remove_unused);

                    Console.WriteLine("Example 6: extracting and applying OCR XML from physics.tif");
                }

            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            //--------------------------------------------------------------------------------
            // Example 7) Check whether a page needs OCR before running it, to avoid unnecessary OCR processing on pages that already contain extractable text
            try
            {
                // lorem_ipsum.pdf already exists in the general TestFiles folder, so it is
                // referenced there instead of duplicating it into the OCR-specific TestFiles/OCR folder.
                string test_files_path = "../../../../TestFiles/";

                // lorem_ipsum.pdf is a scanned document with no extractable text, so it should need OCR.
                using (PDFDoc scannedDoc = new PDFDoc(test_files_path + "lorem_ipsum.pdf"))
                {
                    Page scannedPage = scannedDoc.GetPage(1);

                    // Ask OCRModule whether the page needs OCR. Passing accept_invisible_text as false
                    // means invisible text (e.g. from a prior OCR pass) is ignored and only visible content
                    // is considered, while true would treat an existing invisible text layer as sufficient
                    // to consider the page as not needing OCR.
                    bool scannedNeedsOCR = OCRModule.PageNeedsOCR(scannedPage, false);
                    Console.WriteLine("Example 7: page 1 of lorem_ipsum.pdf " + (scannedNeedsOCR ? "needs" : "does not need") + " OCR");

                    // Only run OCR if it is actually needed
                    if (scannedNeedsOCR)
                    {
                        OCROptions opts = new OCROptions();
                        if(use_iris) opts.SetOCREngine("iris");
                        opts.AddLang("eng");
                        OCRModule.ProcessPDF(scannedDoc, opts);
                        scannedDoc.Save(output_path + "lorem_ipsum_conditional.pdf", SDFDoc.SaveOptions.e_remove_unused);
                    }
                }
            }
            catch (PDFNetException e)
            {
                Console.WriteLine(e.Message);
            }

            PDFNet.Terminate();
        }

    }
}