I used -psm with option from 0 through 5 and only 1, 3, 4 and 5 produce output file. With option 1 and 3 produce the most readable outcome as following.
KFS :Procuflment Card Imps://kfs-prod.adminspps.comell.=d|l/kfs/finxncizl.1’mcmment€ard.d . mm," 1W m Hm Pmnmmt cml IE mam as am: mammal/241mm explm .. whpu .u , ' mama ma Dou-lull m V m N on"... m... - mm: mmummmmmlm \ On Wednesday, November 23, 2016 at 6:10:44 PM UTC-5, Reinaldo Crespo wrote: > > Have you tried different page segmentation modes? > > Execute tesseract from command prompt and take a took at -psm parameter > options. Report here what works best. > > > > > > On Wednesday, November 23, 2016 at 4:12:56 PM UTC-5, Eggo chen wrote: >> >> Hi All, >> I am new to tesseract and need to process a pdf file using >> tesseract. I convert the pdf file into png (shw in below)and run through >> tesseract but the result is not perfect. How can I make this to work? >> Thank you very much in advance. >> >> I am using Tesseract Open Source OCR Engine v3.04.00 with Leptonica. >> >> >> >> >> -- 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 https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/1dcbda25-4404-416c-b0a5-19b346e14ebf%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
