Hi, I try to convert PDF (aspose pdf 11.9.0) with Hocr generated from Tesseract 3.0.4. - With Html hocr : do it nothing ! PDF is same before the transform. - With xhtml hocr : convert method throw FormatException. y…...Default)) using ( var bitmap = new Bitmap (img)) using ( var page...page = ocr.Process(bitmap)) { return page.GetHOCRText(0); } }...