Important Update
We regularly create and update our sample code library so you may quickly learn PDF and OCR (optical character recognition) with PDF extractor SDK and the step-by-step process in C++. PDF and OCR (optical character recognition) with PDF extractor SDK in C++ can be applied with ByteScout Premium Suite. ByteScout Premium Suite is the bundle that includes twelve SDK products from ByteScout including tools and components for PDF, barcodes, spreadsheets, screen video recording.
Save time on writing and testing code by using the code below and use it in your application. Just copy and paste this C++ sample code to your C++ application’s code editor, add a reference to ByteScout Premium Suite (if you haven’t added yet) and you are ready to go! Enjoy writing a code with ready-to-use sample C++ codes to implement PDF and OCR (optical character recognition) with PDF extractor SDK using ByteScout Premium Suite.
Our website gives free trial version of ByteScout Premium Suite. It includes all these source code samples with the purpose to assist you with your C++ application implementation.
On-demand (REST Web API) version:
Web API (on-demand version)
On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)
#include "stdafx.h"
#include "comip.h"
#import "c:\\Program Files\\Bytescout PDF Extractor SDK\\net4.00\\Bytescout.PDFExtractor.tlb" raw_interfaces_only
using namespace Bytescout_PDFExtractor;
int _tmain(int argc, _TCHAR* argv[])
{
// Initialize COM.
HRESULT hr = CoInitializeEx(NULL, COINIT_APARTMENTTHREADED);
// Create the interface pointer.
_TextExtractorPtr pITextExtractor(__uuidof(TextExtractor));
// Set the registration name and key
// Note: You should use _bstr_t or BSTR to pass string to the library because of COM requirements
_bstr_t bstrRegName(L"DEMO");
pITextExtractor->put_RegistrationName(bstrRegName);
_bstr_t bstrRegKey(L"DEMO");
pITextExtractor->put_RegistrationKey(bstrRegKey);
// Load sample PDF document
_bstr_t bstrPath(L"..\\..\\sample_ocr.pdf");
pITextExtractor->LoadDocumentFromFile(bstrPath);
// Enable Optical Character Recognition (OCR)
// in .Auto mode (SDK automatically checks if needs to use OCR or not)
pITextExtractor->put_OCRMode(OCRMode_Auto);
// Set the location of OCR language data files
_bstr_t bstrOCRLangDataPath(L"c:\\Program Files\\Bytescout PDF Extractor SDK\\ocrdata");
pITextExtractor->put_OCRLanguageDataFolder(bstrOCRLangDataPath);
// Set OCR language
_bstr_t bstrOCRLanguage(L"eng");
pITextExtractor->put_OCRLanguage(bstrOCRLanguage);
// Set PDF document rendering resolution
pITextExtractor->put_OCRResolution(300);
// You can also apply various preprocessing filters
// to improve the recognition on low-quality scans.
_ImagePreprocessingFiltersCollection* pIImagePreprocessingFilters;
pITextExtractor->get_OCRImagePreprocessingFilters(&pIImagePreprocessingFilters);
// Automatically deskew skewed scans
//pIImagePreprocessingFilters->AddDeskew();
// Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentation errors)
//pIImagePreprocessingFilters->AddVerticalLinesRemover();
//pIImagePreprocessingFilters->AddHorizontalLinesRemover();
// Repair broken letters
//pIImagePreprocessingFilters->AddDilate();
// Remove noise
//pIImagePreprocessingFilters->AddMedian();
// Apply Gamma Correction
//pIImagePreprocessingFilters->AddGammaCorrection();
// Add Contrast
//pIImagePreprocessingFilters->AddContrast(20);
// (!) You can use new OCRAnalyser class to find an optimal set of image preprocessing
// filters for your specific document.
// See "OCR Analyser" example.
// Save extracted text to file
_bstr_t bstrOutputFile(L"output.txt");
pITextExtractor->SaveTextToFile(bstrOutputFile);
pITextExtractor->Release();
CoUninitialize();
return 0;
}
60 Day Free Trial or Visit ByteScout Premium Suite Home Page
Explore ByteScout Premium Suite Documentation
Explore Samples
Sign Up for ByteScout Premium Suite Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
// stdafx.cpp : source file that includes just the standard includes
// CPPExample.pch will be the pre-compiled header
// stdafx.obj will contain the pre-compiled type information
#include "stdafx.h"
// TODO: reference any additional headers you need in STDAFX.H
// and not in this file
60 Day Free Trial or Visit ByteScout Premium Suite Home Page
Explore ByteScout Premium Suite Documentation
Explore Samples
Sign Up for ByteScout Premium Suite Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
// stdafx.h : include file for standard system include files,
// or project specific include files that are used frequently, but
// are changed infrequently
//
#pragma once
#include "targetver.h"
#include <stdio.h>
#include <tchar.h>
// TODO: reference additional headers your program requires here
60 Day Free Trial or Visit ByteScout Premium Suite Home Page
Explore ByteScout Premium Suite Documentation
Explore Samples
Sign Up for ByteScout Premium Suite Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
#pragma once
// Including SDKDDKVer.h defines the highest available Windows platform.
// If you wish to build your application for a previous Windows platform, include WinSDKVer.h and
// set the _WIN32_WINNT macro to the platform you wish to support before including SDKDDKVer.h.
#include <SDKDDKVer.h>
60 Day Free Trial or Visit ByteScout Premium Suite Home Page
Explore ByteScout Premium Suite Documentation
Explore Samples
Sign Up for ByteScout Premium Suite Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
60 Day Free Trial or Visit ByteScout Premium Suite Home Page
Explore ByteScout Premium Suite Documentation
Explore Samples
Sign Up for ByteScout Premium Suite Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
also available as: