The confidence values embedded in the hOCR output are at the word, not character, level.
On Friday, April 5, 2013 1:52:19 AM UTC-5, satuon wrote: > > I just found out that Tesseract also supports the hOCR format. But I'm not > sure if character-wise confidence levels are available even there. How do I > go about parsing it? > > On Thursday, April 4, 2013 12:00:11 PM UTC+3, priya wrote: >> >> hi, >> >> Does any one know how to find character level confidence, i tried >> "save_blob_choices" code but it gives only word level confidence. Please >> let me know if you hav any pointers. >> > -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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]. For more options, visit https://groups.google.com/groups/opt_out.
