C#: Extract Text from Images or Scanned PDFs with OCR

Install-Package Spire.PDF

using Spire.OCR;
using System.IO;

namespace ReadTextFromImage
{
    internal class Program
    {
        static void Main(string[] args)
        {
            //Specify the path of the input image file
            string imageFilePath = "Image.png";
            //Specify the path of the output text file
            string outputFilePath = "ScanImage.txt";

            //Call the ScanTextFromImage method to scan text from an image
            string scannedText = ScanTextFromImage(imageFilePath);

            //Write the text to the specified file
            File.WriteAllText(outputFilePath, scannedText);
        }

        public static string ScanTextFromImage(string imageFilePath)
        {
            //Instantiate an OcrScanner object
            using (OcrScanner ocrScanner = new OcrScanner())
            {
                //Scan text from the image
                ocrScanner.Scan(imageFilePath);

                //Get the recognized text from the OcrScanner object
                IOCRText text = ocrScanner.Text;

                //Return the text
                return text.ToString();
            }
        }
    }
}

using Spire.OCR;
using System.Collections.Generic;
using System.IO;

namespace ReadTextFromImageWithCoordinates
{
    internal class Program
    {
        static void Main(string[] args)
        {
            //Specify the path of the input image file
            string imagePath = "Image.png";
            //Specify the path of the output text file
            string outputFile = "ScanImageWithCoordinates.txt";

            //Call the ScanTextFromImageWithCoordinates method to extract text and its area information from the image
            List<string> extractedText = ScanTextFromImageWithCoordinates(imagePath);

            //Write the result to the specified file
            File.WriteAllLines(outputFile, extractedText);
        }

        //Retrieve the text blocks along with their location information (x, y, width, height) from an image
        public static List<string> ScanTextFromImageWithCoordinates(string imageFilePath)
        {
            //Create a list
            List<string> extractedText = new List<string>();

            //Instantiate an OcrScanner object
            using (OcrScanner ocrScanner = new OcrScanner())
            {
                //Scan text from the image
                ocrScanner.Scan(imageFilePath);
                //Get the scanned text
                IOCRText text = ocrScanner.Text;

                //Iterate through each text block
                foreach (IOCRTextBlock block in text.Blocks)
                {
                    //Append the text of each block and its location information to the list
                    extractedText.Add($"Text: {block.Text}\nRectangular Area: {block.Box}");
                }
            }

            return extractedText;
        }
    }
}

using Spire.OCR;
using Spire.Pdf;
using System.Collections.Generic;
using System.Drawing;
using System.Drawing.Imaging;
using System.IO;

namespace ReadTextFromScannedPDF
{
    internal class Program
    {
        static void Main(string[] args)
        {
            //Specify the path of the scanned PDF file
            string pdfFilePath = "Sample.pdf";
            //Specify the path of the output text file
            string outputFilePath = "ScanPDF.txt";

            //Extract text from the scanned PDF
            List<string> extractedText = ExtractTextFromScannedPDF(pdfFilePath);

            //Write the text to the specified file
            File.WriteAllLines(outputFilePath, extractedText);
        }

        //Extract text from a scanned PDF
        public static List<string> ExtractTextFromScannedPDF(string pdfFilePath)
        {
            //Create a list to store the extracted text
            List<string> extractedText = new List<string>();

            //Create an instance of the PdfDocument class
            using (PdfDocument document = new PdfDocument())
            {
                //Load the PDF document
                document.LoadFromFile(pdfFilePath);

                //Iterate through each page of the document
                for (int pageIndex = 0; pageIndex < document.Pages.Count; pageIndex++)
                {
                    //Convert the page to an image
                    using (Image image = document.SaveAsImage(pageIndex, 300, 300))
                    {
                        //Create a memory stream to hold the image data
                        using (MemoryStream stream = new MemoryStream())
                        {
                            //Save the image to the memory stream in PNG format
                            image.Save(stream, ImageFormat.Png);
                            stream.Position = 0;

                            //Scan the text from the image and add it to the list
                            string text = ScanTextFromImageStream(stream);
                            extractedText.Add(text);
                        }
                    }
                }
            }

            //Return the list
            return extractedText;
        }

        //Scan text from an image stream
        public static string ScanTextFromImageStream(Stream stream)
        {
            //Create an instance of the OcrScanner class
            using (OcrScanner ocrScanner = new OcrScanner())
            {
                //Scan the text from the image stream in PNG format
                ocrScanner.Scan(stream, OCRImageFormat.Png);
                IOCRText text = ocrScanner.Text;

                //Return the text
                return text.ToString();
            }
        }
    }
}