No. I'm really Sorry about complaining about tesseract(4.0) I mean that tesseract is great , but is not perfect(100%)
I think that Tesseract is fairy good. But, I have a clue about customizing and using Tesseract(4.0) rightfully Thank U. At first I know the trainneddata is 3 types tessdata / tessdata_fast/ tessdata_best / so, I used tessdata - kor.trainneddata to check tesseract(4.0) test .. and you give me a right answer about using tesseract .(another questions I wrote to you) <https://lh3.googleusercontent.com/-LJk-KTYwO8M/Wpf00BT2O5I/AAAAAAAAMw0/3VfqA5FPzd8Ued9xBWcF1VrvNKm9NKz5wCLcBGAs/s1600/0301_2.png> But, you suggest use tessdata_fast ????? I have no idea ...... ㅜㅜㅜ And. once upon a time I used tessdata_best / tessdata_fast /tessdata 3 type use respectively, But correctness is the best data is tessdata .......... <https://lh3.googleusercontent.com/-_PSt4nXFW2U/Wpf1mHFHAiI/AAAAAAAAMxA/zPfyMZG-j14kqwb85eOR0ALF3TwfvSm2gCLcBGAs/s1600/0301_1.png> In the github page descption says that tessdata_best is best accuracy in 3 types tessdata... But in actual is not right .ㅜㅜ Correct rate is fairy different tessdata from tessdata_best So I use the tessdata . What makes me give me a that result So. your last (recently) answer & sugestion = in this passage you give me a suggestion that in the command line to type " combine_tessdata -u kor.traineddata What is that meaning ? Could you explain for me ? (in short) 1. I want to tesseract 4.0 using rightly in my business so i have a plan using trainneddata. case #1 if already made and uploaded github page - 3 type trainned data( tessdata / tessdata_best / tessdata_fast) is not good enough to use Korean in my business I would to make a customized and trainned "New trainneddata" But how can i make a decsion about that / I can make a treshold to help a descision ???? Plz help me .... ㅜㅜ 2018년 3월 1일 목요일 오후 4시 17분 41초 UTC+9, shree 님의 말: > > >we don't understand each otehr saying. > > Sorry about that. > > Please give the following commands and let me know the result. > > tesseract -v > > tesseract --list-langs > > combine_tessdata -u kor.traineddata > > I do not know Korean, but feedback from other users has been that > tesseract4 and the latest trainedadata give good results. > > > >your last command line means that install language pack in tessdata > directory - kor.traineddata > > >I want to say I use that way. but, my test image recognizision rate is > not enough to use the business . > > > There are three sets of traineddata files, in tessdata, tessdata_best and > tessdata_fast repositories on github. > > I was suggesting that you use the ones from tessdata_fast, which are > packaged by AlexanderP for older versions of Linux along with the latest > version of the programs. > > I am attaching a test image and the results that I get using Tesseract. To > me the accuracy looks good, whether that is acceptable for use in business > is a decision you have to make. > > > > > > ShreeDevi > ____________________________________________________________ > भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com > > On Thu, Mar 1, 2018 at 11:30 AM, 이경준 <[email protected] <javascript:>> > wrote: > >> Thank U . for advice >> >> I have never installed tesseract (3.0x) >> >> I have a question >> >> your last command line means that install language pack in tessdata >> directory - kor.traineddata >> >> Am I false. >> >> I want to say I use that way. but, my test image recognizision rate is >> not enough to use the business . >> >> we don't understand each otehr saying. >> >> Thank u >> >> 2018년 3월 1일 목요일 오후 2시 30분 11초 UTC+9, shree 님의 말: >> >>> > my system is operated by Ubuntu 16.04. 03 LTS >>> >>> > Yes .I tried tessdata - kor.trainnedata /// But it is not good >>> enough. sorry .ㅜㅜ i can not use tesseract 4.0 tessdata-kor.trainnedata. in >>> bussiness .. >>> >>> I will suggest that you uninstall your old tesseract version.(3.0x) >>> >>> >>> sudo apt-get remove tesseract-ocr >>> >>> >>> and then install tesseracr4.00 version from the PPA provided by >>> AlexanderP >>> >>> sudo add-apt-repository ppa:alex-p/tesseract-ocr >>> sudo apt-get update >>> >>> sudo apt-get install tesseract-ocr >>> >>> sudo apt-get install tesseract-ocr-kor >>> >>> >>> >>> -- >> 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] <javascript:>. >> To post to this group, send email to [email protected] >> <javascript:>. >> 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/f1de33d0-e0c4-4d65-88b4-57c92562ea8a%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/f1de33d0-e0c4-4d65-88b4-57c92562ea8a%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/152b6fb1-bfcb-4ab5-9123-aeb9061e2dd5%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
