[tesseract-ocr] How to merge 2 traineddata into 1 traineddata

Hi I'm newbie. I'm interested in tesseract 4.00 _beta.1 I have a question How to merge 2 traineddata into 1 traineddata ? I don't want to use command line option lie -l eng+chi_tra Thank You -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group.

Re: [tesseract-ocr] How to merge 2 traineddata into 1 traineddata

Thank you for answer myquestion. but, i mistake write there I want to korean + english . the way to merge traineddata is the same ? 2018년 3월 26일 월요일 오후 6시 15분 0초 UTC+9, shree 님의 말: > > Try the script level traineddata files from tessdata_fast/script > > Han probably has eng+chi* > > ShreeD

Re: [tesseract-ocr] How to merge 2 traineddata into 1 traineddata

Thank you so much. Have a nice day~ 2018년 3월 26일 월요일 오후 6시 41분 18초 UTC+9, shree 님의 말: > > Please look at > https://github.com/tesseract-ocr/tessdata_fast/tree/master/script > > Look at all Han* files > > maybe Hangul is the one you need. > > See https://github.com/tesseract-ocr/tessdata_fast/blob

Re: [tesseract-ocr] How to merge 2 traineddata into 1 traineddata

Hi Sorry could I qeustion one ? I SAW THE README.MD PAGE but,I want to merge 2 traineddata which I made manually EITHER IS IT POSSIBLE? THANK U -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving

[tesseract-ocr] How to recognize only trained images (100% recognization rate By using tesseract 4.00 (images tesseract trained))

Hi I have a question about tesseract . For example I have an 500 images They are captured images in the web. and they are not hand-written. So, I just want to tesseract to recognize these images. for this purpose, I jsut train thess images ? How to recognzie only trained images ? I wan

[tesseract-ocr] Re: How to recognize only trained images (100% recognization rate By using tesseract 4.00 (images tesseract trained))

I have no idea about LSTM , DEEP LEARNING IT MEANS OVERFIT ? OVERTRAIN Could you tell me the answer ? I just want to tesseract to guarantee 100% my images (I owned) Thank You 2018년 3월 27일 화요일 오전 9시 15분 28초 UTC+9, notorio...@gmail.com 님의 말: > > Hi > > I have a question about tesseract . > >

[tesseract-ocr] after command line type " lstmtraining ~~~ " , There is no changes. no logs.

Hi. After rendering by using tesstrain.sh And I type lstmtraining --debug_interval 100 --traineddata /usr/share/tesseract-ocr/4.00/tessdata/tesseract/training/trained_plus_chars_kor/kor/kor.traineddata --net_spec '[1,36,0,1 Ct3,3,16 Mp3,3 Lfys48 Lrx96 Lfx256 01c111]' --model_output /usr/sha

[tesseract-ocr] Hi Could you tell me way to install ScrollView.jar ?

Hi Could you tell me way to install ScrollView.jar ? I saw the tesseract github page But, I could n't make sense I installed tesseract 4.00 .beta.1 // and I clone git (1) langdata/ 2) tesseract) ubuntu 16.04.03. LTS Thank you -- You received this message because you are subscribed to the G

[tesseract-ocr] I want to traineddata from scratch. I have to install ScrollView.jar

Hi. I have an question .. I want to traineddata from scratch. I have to install S

[tesseract-ocr] on the lstmtraiing, Have you ever seen error like "Logisitc outputs not implemented yet!"

Hi All on the lstmtraiing, Have you ever seen error like "Logisitc outputs not implemented yet!" // Performs forward-backward on the given t

[tesseract-ocr] lstmtraining command line related

I type the command line in my computer ubuntu 16.04.03 LTS sudo lstmtraining --debug_interval -1 --traineddata /usr/share/tesseract-ocr/4.00/tessdata/kor.traineddata --net_spec* '[1,0,0,1 Ct5,5,16 Mp3,3 Lfys64 Lfx128 Lrx128 Lfx256 01c105]'* --train_listfile /usr/share/tesseract-ocr/4.00/tessd

[tesseract-ocr] Re: lstmtraining command line related

*Invalid network spec:01c105]* *Missing ] at end of [Series]!* *Failed to create network from spec: [1,0,0,1 Ct5,5,16 Mp3,3 Lfys64 Lfx128 Lrx128 Lfx256 01c105]* 2018년 3월 28일 수요일 오후 3시 53분 17초 UTC+9, notorio...@gmail.com 님의 말: > > I type the command line in my computer ubuntu 16.04.03 LTS > > su

[tesseract-ocr] What is the exact role of the '(lang).wordlist'

What is the exact role of the '(lang).wordlist' I have no idea (lang).wordlist?? It can help tesseract 4.00 to process *postprocessing ?? * *like dictionary??? * -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group

[tesseract-ocr] tesstrain.sh (train vs eval)

안녕하세요. 렌더링을 통한 훈련과 테스트 데이터를 만드는 과정에서, 이 둘의 관계는 딥러닝의 관점에서 사용되는 증명의 관계인가요? 아니면 진짜 테스트 데이터를 만들어서 테스트 하기 위한 관계인가요? 일반적으로 훈련데이터에 사용되지 않는 테스트 데이터를 만들고, 훈련데이터와 테스트 데이터를 6:4 비율로 만드는 일반적인 딥러닝 훈련과정속에서 In the process of creating training and testing data through rendering(tesstrain.sh), is the relatio

Re: [tesseract-ocr] Re: lstmtraining command line related

@Shree I want to make a traineddata Could I have one more question about training from scratch ? I execute that command line lstmtraining —debug_interval -1 —traineddata /usr/share/tesseract-ocr/4.00/tessdata/kor.traineddata —model_output /home/inplat/tesstutorial/koroutput/base —learning_rate

[tesseract-ocr] same traningdata, same condtion etc ... But only different 'net spec' affects overall tesseract's recognize rate ?

same traningdata, same condtion etc ... But only different 'net spec' affects overall tesseract's recognize rate ? Do the other variables and conditions remain the same and do different net specs affect the overall engine recognition rate? -- You received this message because you ar

[tesseract-ocr] in the tesseract 4.00 beta.1 - when training from scratch /// When kor.unicharset (= (lang).unicharset) is used ?

Hi . I 'm newbie in the tesseract 4.00 beta.1 - when training from scratch /// When kor.unicharset (= (lang).unicharset) is used ? Could you tell me details? Thank you -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from

[tesseract-ocr] Is it possible to modify tesstrain.sh for using images I owned(I made box/tif manually)

Hi Shree Is it possible to modify tesstrain.sh for using images I owned(I made box/tif manually) https://github.com/tesseract-ocr/tesseract/issues/841 I saw the this article , But could you tell me more detail ? Thank you -- You received this message because you are subscribed to the Go

[tesseract-ocr] When tesseract(3.04) makes a box, is there a way to control it if it is made more than the number of letters?

Hi When tesseract(3.04) makes a box, is there a way to control it if it is made more than the number of letters? The original image contains eight characters, but tesseract(3.04) has nine boxes. So I only put 8 boxes of file information into the box file, but A showed 9 characters in the exe

[tesseract-ocr] Re: When tesseract(3.04) makes a box, is there a way to control it if it is made more than the number of letters?

The original image contains eight characters, but tesseract(3.04) has nine boxes. = The original image contains eight characters, but tesseract(3.04) makes nine boxes. ($ tesseract (lang).(fontname).exp(num).tif tesseract (lang).(fontname).exp(num) -l lang batch.nochop makebox) 2018년 4월 2일 월

[tesseract-ocr] in the script data directory , script data of English is Latin.traineddata ?

Hi in the script data directory(tess_best/script) , script data of English is Latin.traineddata ? waiting for answer. Thank you -- 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