Convert Scanned PDF to Text in C# .NET

readme.md

For more details, please visit Convert Scanned PDF File to Text in C#

Scanned-PDF-to-Text-File.cs

// Initialize AsposeOcr class instance
AsposeOcr api = new AsposeOcr();

// Recognize images from PDF           
DocumentRecognitionSettings set = new DocumentRecognitionSettings();
set.DetectAreas = false;

// Save recognition results
List<RecognitionResult> result = api.RecognizePdf("multi_page_1.pdf", set);

// Initialize StringBuilder class object
StringBuilder builder = new StringBuilder();

// Save result in a TXT file
foreach (RecognitionResult page in result)
{
    builder.Append(page.RecognitionText);
}

System.IO.File.WriteAllText("Text.txt", builder.ToString());

Scanned-PDF-to-Text.cs

// Initialize AsposeOcr class instance
AsposeOcr api = new AsposeOcr();

// Specify the setting for recognizing the scanned PDF file
DocumentRecognitionSettings set = new DocumentRecognitionSettings();
set.DetectAreas = false;

// Initialize RecognitionResult class object
List<RecognitionResult> result = api.RecognizePdf("pages.pdf", set);

// Print text after recognizing it from scanned PDF
int pageNumber = 0;
foreach (RecognitionResult page in result)
{
    System.Console.WriteLine($"Page: {pageNumber++} text: {page.RecognitionText}");
}