Have given it a try. The output is now in one block as needed, thats good.
But the problem now seems to be that it does not take my training data into much account. Special chars are no longer reconized. I guess the "-psm 6" option makes it stop earlier in the process. It it possible to just make it skip the segmentation process and have the rest as usual ? I am just taking a pure guess here on how it works. Benjamin Den fredag den 3. januar 2014 20.02.24 UTC+1 skrev Benjamin Sølberg: > > Thank you, i'll try that. > > Is it possible to achieve the same functionality by using a config > parameter as I also need to run this on an iPhone ? > > Regards > Benjamin > > Den fredag den 3. januar 2014 17.48.06 UTC+1 skrev Quan Nguyen: >> >> Try with PSM 4, 5, or 6. >> >> On Thursday, January 2, 2014 6:12:53 PM UTC-6, Benjamin Sølberg wrote: >> >>> Hi all >>> >>> I am training tesseract to work with a custom font. >>> Things are moving forward but there are clouds in the sky. >>> >>> When using tesseract it insists to cut the texts into sections. >>> I understand why as the textual layout may seems to be column based. >>> The text is very much like an excel sheet with columns. >>> But I would very much like tesseract to give me all the text in one >>> giant line based blob instead of many sections. >>> >>> Is it possible to make tesseract not chop up the image into (columns in >>> my case) ? >>> >>> Regards >>> Benjamin >>> >>> -- -- 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.
