On Sat, May 6, 2017 at 8:24 PM, <[email protected]> wrote: Should I add boxes with spaces before punctuation marks? >
If there is a space before the punctuation mark in text, then you should. > > Also I've found this discussion: > https://github.com/tesseract-ocr/tesseract/issues/841 > > It helped me a lot, but I still got questions. > What should I put in rus.training_text, if I want to generate .lstmf files > from my own box/tiff pairs? Texts from images? > If you want to train solely based on your images, just use the default training text from langdata and one font, and use the modified shell script to train with copied box/tiff pairs and this file. Then as described in the discussion at 841, build your training_files.txt file by using appropriate names for your box/tiff pairs only. eg. my copied box/tiff pairs were named as eng.1852nyd*.tif, while the generated file was eng.Arial.exp0.tif. By using the following command, I created the training_files,txt. sudo ls -1 ~/tesstutorial/nydFT/eng.1852*.lstmf > ~/tesstutorial/nydFT/nyd.training_files.txt Possibly, you can directly edit that file and only keep the files you want on the list, but on my PC I haven't been able to get i to work - the edited file gives error, hence I use `ls` command to build it. Experiment with a small file and adjust to get the output you want. > > суббота, 6 мая 2017 г., 17:13:29 UTC+5 пользователь shree написал: >> >> When using pre-existing box tiff pairs, you have to add a box with tab >> character to mark end of line and also add boxes with spaces after every >> word. >> >> You then need to generate the .lstmf files - please >> see training/tesstrain.sh for details. >> >> ShreeDevi >> ____________________________________________________________ >> भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com >> >> On Sat, May 6, 2017 at 4:40 PM, bmwmine <[email protected]> wrote: >> >>> you are missing the .lstmf files >>> >>> -- >>> 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/ms >>> gid/tesseract-ocr/47875785-3322-4d5d-89fd-1818c2c06bc2%40goo >>> glegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/47875785-3322-4d5d-89fd-1818c2c06bc2%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> -- > 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/35ecde41-d654-408d-bd98-7de37fc6684a% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/35ecde41-d654-408d-bd98-7de37fc6684a%40googlegroups.com?utm_medium=email&utm_source=footer> > . > > For more options, visit https://groups.google.com/d/optout. > -- 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/CAG2NduV%2BsgV5sj%2Bc9HtPEVKDYvHPcyktLpYtrq%3DJ6VdbKWR1dQ%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
