[tesseract-ocr] Re: train tesseract OCR 4.0

2020-02-22 Thread saman ukh
Hello all, I am using tesseract 4.0 which uses LSTM I have searched a lot for training new characters, unfortunately, I found difficult to do training I am trying to train Arabic Traineddata by adding a few new characters can anyone help me with this what are the steps, where to start? On

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-25 Thread Saurabh Srivastav
Edit your box files with correct data and the make a traineddata file and then paste it to usr/local/share/tessdata On Wednesday, April 12, 2017 at 3:39:01 PM UTC+5:30, srn...@gmail.com wrote: > > I am able to train the tesseract with fine tuning technique with some > training text (not

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-12 Thread srnsp92
I am able to train the tesseract with fine tuning technique with some training text (not images).. and i want to know how train tesseract with images and box files.. I am getting confused because when i give this tesseract ara.arial.exp4.tif ara.arial.exp4 nobatch box.train command, tr files

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-10 Thread Saurabh Srivastav
hello srn , can you please let me know about your progress... -- 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

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread srnsp92
Hello ShreeDevi, I solved this error lstm.train, i have given wrong path. mkdir -p ~/tesstutorial/engoutput training/lstmtraining *-U ~/tesstutorial/engtrain/eng.unicharset \* --script_dir ../langdata --debug_interval 100 \* --net_spec '[1,36,0,1 Ct5,5,16 Mp3,3 Lfys64 Lfx128 Lrx128 Lfx256

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread srnsp92
Please tell and help me how can i get LSTM.train config file.. as i need to work on Tesseract 4 only... dont have other option On Wednesday, April 5, 2017 at 1:59:56 PM UTC+5:30, shree wrote: > > You do not have the LSTM.train config file. > > - excuse the brevity, sent from mobile > > On

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread srnsp92
Overview of Training Process The overall training process is similar to training 3.04 Conceptually the same: 1. Prepare training text. 2. Render text to image + box file. (Or create hand-made box files for existing

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread ShreeDevi Kumar
You do not have the LSTM.train config file. - excuse the brevity, sent from mobile On 05-Apr-2017 1:55 PM, wrote: > After u have said, > > I tried in two ways and i am stuck at lstm step: > > Training > > command used: > >

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread ShreeDevi Kumar
4.0 is alpha software. Please use an older released version. - excuse the brevity, sent from mobile On 05-Apr-2017 1:55 PM, wrote: > After u have said, > > I tried in two ways and i am stuck at lstm step: > > Training > > command used: > >

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-05 Thread srnsp92
After u have said, I tried in two ways and i am stuck at lstm step: Training command used: /home/p/Documents/T/tesseract-master/training/lstmtraining -U /home/p/Documents/T/img_frm_3/eng.unicharset \ > --script_dir /home/p/Documents/T/TESS_4_ALPHA/langdata-master --debug_interval 100 \ >

Re: [tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-04 Thread ShreeDevi Kumar
Read https://github.com/tesseract-ocr/tesseract/wiki/4.0-with-LSTM https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00 https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00---Finetune

[tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-04 Thread srnsp92
Can you please post some experiences in this post, as there are no posts to train tesseract 4. 1)And also, is there any way to add the new trained data file to old trained data file, without replacing the old file. 2)If we dont know what font we may get in our images, then how should we

[tesseract-ocr] Re: train tesseract OCR 4.0

2017-04-04 Thread Saurabh Srivastav
Yes, i trained my tesseract for eng font and make them read the characters from image. > thanks, >> Saurabh Srivastav >> > -- 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