Inscriptions will be like training for handwriting. I have not tried any LSTM training with scanned images.
Please see https://github.com/tesseract-ocr/tesseract/wiki/VGSLSpecs You can try experimenting with different network specs based on the type of input you have. On Wed, Mar 13, 2019 at 7:24 AM Naga raja <[email protected]> wrote: > Thanks for the response. Following are the response to your questions. > Basically we had doubt on sizes while training a new script sample in LSTM. > > On Tuesday, March 12, 2019 at 2:00:49 PM UTC+9, shree wrote: >> >> 1. Which ancient scripts are you trying to train? >> >> Tamil scripts which present in inscriptions > > 2. Are you trying to train base tesseract (3.0x) or LSTM tesseract? >> >> .LSTM tesseract > > >> 3. Are you using synthetic traineddata using text2image or scanned images? >> >> Scanned Images. > > > >> On Tue, Mar 12, 2019 at 10:16 AM Naga raja <[email protected]> wrote: >> >>> Hi All, >>> >>> As we are working in some ancient scripts, even after training lots of >>> data we found that the accuracy is very very less. >>> >>> We would like to know what is the recommended box size of each character >>> and what would be the best resolution to train in tesseract. >>> >>> Thanks in Advance. >>> >>> -- >>> 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/ad7658a8-fabf-4632-a290-5b7a7d97680b%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/ad7658a8-fabf-4632-a290-5b7a7d97680b%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> >> -- >> >> ____________________________________________________________ >> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >> > -- > 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/007852ff-4240-47c0-b1ad-4cda885609e2%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/007852ff-4240-47c0-b1ad-4cda885609e2%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com -- 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/CAG2NduWaCV0kTzdCAhc4HPf_DkThyV2RdSik-TtTJTEjBQVdUw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
