ocr-tesseract/Form1.cs

using System.Diagnostics;
using System.Windows.Forms;
using Inlite.ClearImageNet;
using Tesseract;

namespace WinFormsApp3
{
    public partial class Form1 : Form
    {
        private readonly string _basePath;
        private readonly string _tessDataPath;

        public Form1()
        {
            InitializeComponent();

            _basePath = Path.GetFullPath(Path.GetDirectoryName(Application.ExecutablePath) + "\\..\\..\\..\\");
            _tessDataPath = Path.Combine(_basePath, "#research", "tessdata");
        }

        protected override void OnLoad(EventArgs e)
        {
            base.OnLoad(e);

            richTextBox1.Clear();
        }

        private void button1_Click(object sender, EventArgs e)
        {
            var testImagePath = Path.Combine(_basePath, "#research", "Passport Demand Study Sample Letter.jpg");

            richTextBox1.Text += ParseOCR(testImagePath);
            richTextBox1.Text += Environment.NewLine;
        }

        private void button2_Click(object sender, EventArgs e)
        {
            var testImagePath = Path.Combine(_basePath, "#research", "Passport Demand Study Sample Letter.jpg");

            var barcodes = ReadBarcode(testImagePath);
            foreach (var barcode in barcodes)
            {
                richTextBox1.Text += $"Barcode Type = {barcode.Type} | Value = {barcode.Text} | Page = {barcode.Page}";
                richTextBox1.Text += Environment.NewLine;
            }
        }

        private void button3_Click(object sender, EventArgs e)
        {
            var testImagePath = Path.Combine(_basePath, "#research", "Passport Demand Study Sample Letter.jpg");

            richTextBox1.Text += Environment.NewLine;

        }

        ////var basePath = Path.GetFullPath(Path.GetDirectoryName(Application.ExecutablePath) + "\\..\\..\\..\\");


        ////var tt2 = File.Exists(testImagePath);

        //try
        //{
        //    using (var engine = new TesseractEngine(_tessDataPath, "eng", EngineMode.Default))
        //    {
        //        using (var img = Pix.LoadFromFile(testImagePath))
        //        {
        //            using (var page = engine.Process(img))
        //            {
        //                Console.WriteLine("Mean Confidence = {0}", page.GetMeanConfidence());

        //                //var tt1 = page.GetLSTMBoxText(0);
        //                //var tt1 = page.GetAltoText(0);
        //                //var tt1 = page.GetBoxText(0);
        //                //var tt1 = page.GetHOCRText(0);
        //                //var tt1 = page.GetMeanConfidence();
        //                var tt1 = page.GetText();
        //                //var tt1 = page.GetUNLVText();




        //                //Console.WriteLine("Text (GetText): \r\n{0}", text);
        //                //Console.WriteLine("Text (iterator):");
        //                //using (var iter = page.GetIterator())
        //                //{
        //                //    iter.Begin();

        //                //    do
        //                //    {
        //                //        do
        //                //        {
        //                //            do
        //                //            {
        //                //                do
        //                //                {
        //                //                    if (iter.IsAtBeginningOf(PageIteratorLevel.Block))
        //                //                    {
        //                //                        Console.WriteLine("<BLOCK>");
        //                //                    }

        //                //                    Console.Write(iter.GetText(PageIteratorLevel.Word));
        //                //                    Console.Write(" ");

        //                //                    if (iter.IsAtFinalOf(PageIteratorLevel.TextLine, PageIteratorLevel.Word))
        //                //                    {
        //                //                        Console.WriteLine();
        //                //                    }
        //                //                } while (iter.Next(PageIteratorLevel.TextLine, PageIteratorLevel.Word));

        //                //                if (iter.IsAtFinalOf(PageIteratorLevel.Para, PageIteratorLevel.TextLine))
        //                //                {
        //                //                    Console.WriteLine();
        //                //                }
        //                //            } while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.TextLine));
        //                //        } while (iter.Next(PageIteratorLevel.Block, PageIteratorLevel.Para));
        //                //    } while (iter.Next(PageIteratorLevel.Block));
        //                //}
        //            }
        //        }
        //    }
        //}
        //catch (Exception exc)
        //{
        //    //Trace.TraceError(exc.ToString());
        //    Console.WriteLine("Unexpected Error: " + exc.Message);
        //    //Console.WriteLine("Details: ");
        //    //Console.WriteLine(exc.ToString());
        //}
        //}


        private string ParseOCR(string filename)
        {
            string response = null;

            try
            {
                using (var engine = new TesseractEngine(_tessDataPath, "eng", EngineMode.Default))
                {
                    using (var img = Pix.LoadFromFile(filename))
                    {
                        using (var page = engine.Process(img))
                        {
                            Debug.WriteLine("Mean Confidence = {0}", page.GetMeanConfidence());

                            //var tt2 = page.GetAltoText(0);
                            //var tt3 = page.GetBoxText(0);
                            //var tt4 = page.GetHOCRText(0);
                            //var tt1 = page.GetLSTMBoxText(0);
                            //var tt5 = page.GetMeanConfidence();
                            //var tt7 = page.GetTsvText(0);
                            //var tt6 = page.GetUNLVText();

                            response = page.GetText();
                        }
                    }
                }
            }
            catch (Exception exc)
            {
                // error
            }

            return response;
        }

        private Barcode[] ReadBarcode(string filename)
        {
            var result = new Barcode[0];

            try
            {
                using (BarcodeReader reader = new BarcodeReader())
                {
                    reader.Code39 = true;
                    reader.Code128 = true;
                    reader.Upca = true;
                    reader.Upce = true;
                    reader.QR = true;

                    result = reader.Read(filename, 0);

                    //foreach (var barcode in result)
                    //{
                    //    Debug.WriteLine($"Barcode type: {barcode.Type}  Barcode page: {barcode.Page}  Text: {barcode.Text}");
                    //}
                }
            }
            catch (Exception exc)
            {
                Debug.WriteLine(exc.Message);
            }

            return result;
        }

    }
}