using System; using System.Collections.Generic; //Use following namespace to extract text from scanned PDF using Aspose.OCR; namespace ExtractTextFromScannedPDFFile { class Program { static void Main(string[] args) { //Set license before extracting text from scanned PDF file Aspose.OCR.License AsposeOCRLicense = new Aspose.OCR.License(); AsposeOCRLicense.SetLicense(@"c:\asposelicense\license.lic"); //create AsposeOcr object AsposeOcr ScannedPDFFile = new AsposeOcr(); //set recognition settings DocumentRecognitionSettings RecognitionSettings = new DocumentRecognitionSettings(); RecognitionSettings.StartPage = 1; RecognitionSettings.PagesNumber = 3; //when set true, improves accuracy but reduces speed RecognitionSettings.DetectAreas = false; //extract text from specified pages List<RecognitionResult> ExtractedResults = ScannedPDFFile.RecognizePdf("InputScannedPDFFile.pdf", RecognitionSettings); //fetch extracted text of each page int PageCounter = 1; foreach(RecognitionResult SinglePage in ExtractedResults) { Console.WriteLine("Page: {0}, Extracted Text:{1}", PageCounter, SinglePage.RecognitionText); PageCounter++; } } } }