examples.md

Examples

Notes

• You need trained data in tessdata by language
• You can get them at https://github.com/tesseract-ocr/tessdata or https://github.com/tesseract-ocr/tessdata_fast

Basic Text from Image from filepath

using (var engine = new Engine(@"./tessdata", Language.English, EngineMode.Default))
{
    using (var img = TesseractOCR.Pix.Image.LoadFromFile(testImagePath))
    {
        using (var page = engine.Process(img))
        {
            var text = page.Text;
            Console.WriteLine("Mean confidence: {0}", page.MeanConfidence);
            Console.WriteLine("Text (GetText): \r\n{0}", text);
            Console.WriteLine("Text (iterator):");
        }
    }
}

Basic Text from Image bytes

using (var fs = new FileStream(filename, FileMode.Open, file_access)) ;
using (var ms = new MemoryStream())
{
    fs.CopyTo(ms);
    bytes[] fileBytes = ms.ToArray();
    using (var engine = new Engine(@"./tessdata", Language.English, EngineMode.Default))
    {
        using (var img = TesseractOCR.Pix.Image.LoadFromMemory(fileBytes))
        {
            using (var page = engine.Process(img))
            {
                var txt = page.Text;
            }
        }
    }
}

Image to txt searchable pdf using paths

using (var renderer = TesseractOCR.Renderers.Result.CreatePdfRenderer(@"test.pdf", @"./tessdata", false))
{
    // PDF Title
    using (renderer.BeginDocument("SearchablePdfTest"))
    {
        const string configurationFilePath = @"C:\tessdata";
        using (var engine = new Engine(configurationFilePath, Language.English, EngineMode.TesseractAndLstm))
        {
            using (var img = TesseractOCR.Pix.Image.LoadFromFile(@"C:\file-page1.jpg"))
            {
                using (var page = engine.Process(img, "SearchablePdfTest"))
                {
                    renderer.AddPage(page);
                }
            }
        }
    }
}