I am busy with a project to use OCR on pdf drawings (not scanned) that doesn't have the text in pdf text fields. Currently I am getting results, but I need to improve the results. What typically happens something like APP- is recognized as AQQ- The text I am intrested in is drawings numbers not normal words. The normal words are recongized fairly well. I typically convert the pdf's to 300dpi tiffs, upping the dpi doesn't improve things, it worsens the results for some reason. Should a train tesseract on a higher dpi? The text in the pdf drawings is high quality, but the letters aren't large. Any ideas?
Regards Dewald -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to tesseract-ocr@googlegroups.com To unsubscribe from this group, send email to tesseract-ocr+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en