Re: [tesseract-ocr] Interrupting and restarting lstmtraining

2020-01-06 Thread Adam Funk
Thanks! Unfortunately I'm now getting the dreaded "Failed to read continue from:" error. I have used docker exec to start another terminal in the running container, and am trying to use the following command: lstmtraining \ --stop_training \ --continue_from /data/output/meme_checkpoi

[tesseract-ocr] Re: Using tesseract to extract text from License/Voter ID/PAN Card

2020-01-06 Thread Shubhranshu Panda
I don't know. but you can visit github. some people have shared their work on the same. On Tuesday, 12 June 2018 12:29:09 UTC+5:30, Vidur Malhotra wrote: > > Has anybody developed a solution on the same? > -- You received this message because you are subscribed to the Google Groups "tesseract-

[tesseract-ocr] PANCARD AADHAAR

2020-01-06 Thread Shubhranshu Panda
I don't know how to extract particular text from a standard image type. I want to extract the name, dob and PAN number from the PAN card. I have attachhed a sample image for reference. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubs

Re: [tesseract-ocr] PANCARD AADHAAR

2020-01-06 Thread Suresh Anand
Use NER model after you extract the text with Oct If you are interested in extracting both text and photo them use YOLO object detection and then tesseract On Mon., 6 Jan. 2020, 19:37 Shubhranshu Panda, < shubhranshu.panda...@gmail.com> wrote: > I don't know how to extract particular text from a

Re: [tesseract-ocr] PANCARD AADHAAR

2020-01-06 Thread Shubhranshu Panda
Thanks. Additionally, is there any way I can instruct the system to look for the exact location for text extraction? On Mon 6 Jan, 2020, 7:52 PM Suresh Anand, wrote: > Use NER model after you extract the text with Oct > > If you are interested in extracting both text and photo them use YOLO > ob

Re: [tesseract-ocr] PANCARD AADHAAR

2020-01-06 Thread Suresh Anand
You have annotations tools where you can annotate and train I use labellmg .There are many you can explore On Mon., 6 Jan. 2020, 20:21 Shubhranshu Panda, < shubhranshu.panda...@gmail.com> wrote: > Thanks. > Additionally, is there any way I can instruct the system to look for the > exact location

Re: [tesseract-ocr] Re: Using tesseract to extract text from License/Voter ID/PAN Card

2020-01-06 Thread Suresh Anand
Yes I myself have done this On Mon., 6 Jan. 2020, 19:36 Shubhranshu Panda, < shubhranshu.panda...@gmail.com> wrote: > I don't know. but you can visit github. some people have shared their work > on the same. > > On Tuesday, 12 June 2018 12:29:09 UTC+5:30, Vidur Malhotra wrote: >> >> Has anybody d

Re: [tesseract-ocr] What does ALIGNED TRUTH exactly mean?

2020-01-06 Thread Ashwini Nande
Hi, I need to check for it. On Mon, 6 Jan 2020, 12:23 pm Janghyuk Choi, wrote: > Thank you for your kind reply, Ashwini. > Yeah, I totally agree with your mention. > > And, could you tell me what the *ALIGNED TRUTH* is? > > > 2020년 1월 6일 월요일 오후 2시 21분 52초 UTC+9, Ashwini Nande 님의 말: >> >> Hi, >>

Re: [tesseract-ocr] Re: Using tesseract to extract text from License/Voter ID/PAN Card

2020-01-06 Thread Shubhranshu Panda
Can you please share the process to give us an idea on what the approach should be? On Mon 6 Jan, 2020, 8:57 PM Suresh Anand, wrote: > Yes I myself have done this > > On Mon., 6 Jan. 2020, 19:36 Shubhranshu Panda, < > shubhranshu.panda...@gmail.com> wrote: > >> I don't know. but you can visit gi

[tesseract-ocr] Re: convert a .tiff file to text file

2020-01-06 Thread George Varghese
reason I want to do this : I found that sometime other processes which runs on the same server, gets an exit code of 255 and does not complete. So If I can limit the usage of tesseract to 2 cores and rest available for other processes On Wednesday, January 30, 2019 at 11:34:42 AM UTC-8,

Re: [tesseract-ocr] Re: convert a .tiff file to text file

2020-01-06 Thread Shree Devi Kumar
Have you tried OMP_THREAD_LIMIT=1 On Tue, Jan 7, 2020 at 4:18 AM George Varghese wrote: > > reason I want to do this : > > I found that sometime other processes which runs on the same server, gets > an exit code of 255 and does not complete. So If I can limit the usage of > tesseract to 2 core