Using OCR, it's possible to read the text from an image. However, if the customer has scanned the image in a rotated orientation, the text might not be read correctly. Therefore, a function that returns the orientation of the text in the image—similar to what Tesseract provides—would be highly desirable.

Here's an example:

var ocr = new TesseractEngine(this.tesseractDataPath, this.tesseractLanguage, EngineMode.Default));

// OSD (Orientation and Script Detection) requires training data for orientation recognition.
using (var page = ocr.Process(image, PageSegMode.AutoOsd))
{
    using (var pageIter = page.AnalyseLayout())
    {
        pageIter.Begin();
        var pageProps = pageIter.GetProperties();

        // Get page orientation (Page Up, Page Down, Page Left, Page Right)
        var orientation = pageProps.Orientation;
        Console.WriteLine($"Orientation: {orientation}");
        Console.WriteLine($"DeskewAngle: {pageProps.DeskewAngle}");

        // Rotate image based on DeskewAngle (in radians)
        ////pix.Rotate(pageProps.DeskewAngle);
        return orientation;
    }
}

It would be great to see this feature available in GemBox soon!