If you are familiar with image processing then you can first separate each character and then pass it to Tesseract, it may be helpful, before that binarized input image using Otsu.
On Monday, 22 June 2015 12:12:33 UTC+5:30, Jonathan Frankel wrote: > > Good Day, > > I am trying to do OCR on short words like 'Off'. Even if I set the psm to > assume only a single word, the best result that I get is 'Oll'. > > I have attached the image I am using. If anyone has experience in > improving my results, please advise. > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/07d00efd-dd23-40fa-b383-b156fb32a4a2%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
