[tesseract-ocr] Re: Training error "Couldn't find a matching blob"

[shree]

This has been an issue for long. Thanks for finding the problem.

Please submit a PR on github.

On Friday, June 1, 2018 at 1:55:25 AM UTC+5:30, Paul Kitchen wrote:
>
> After a lot of stepping through tesseract code, I found the problem. 
>
> 1)  In file coutln.cpp, function C_OUTLINE::IsLegallyNested(), we 
> assign outer_area() to an inT32, parent_area. Then lower in the function, 
> we multiple child->outer_area() by parent_area. This caused an integer 
> overflow which resulted in a bad sign for the multiplication. The fix was 
> to make parent_area an inT64 so that integer overflow cannot happen.
>
>
> The two 32-bit integers being multiplied were -51874 and 60218. The true 
> result should be -3123748532 but the maximum result cannot be greater than 
> 2^31 or you will have sign/overflow problems, which is the case here. The 
> computer result was 1171218764, causing the if-statement to go down the 
> wrong path.
>
> dfs
>
>
>
>
>
>
>
>

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/1ef0e822-9518-4cbb-af39-5a8ec6370d00%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

[tesseract-ocr] Preprocess Image

[Hongguo An]

Hi:
When trying to OCR the above image, the date 09/02/2017 is always wrong, 
(0G/02/2017).


This is tesseract 4 running on linux, the cmd line is: 

*tesseract stdin stdout -l eng --psm 11 --oem 1 -c textonly_pdf=1 -c 
tessedit_create_pdf=1 | pdftotext -layout - - *


Is there any way to pre-process the image to make it work? (preferably 
using convert)


Thanks

Hongguo An

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/f77bbd69-a1d2-473c-98ed-fc0ecd9d4034%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

[tesseract-ocr] Re: Not able install tesseract ocr on ubuntu 17.04

[Александр Поздняков]

You need to replace in */etc/apt/sources.list* repository 
*http://us.archive.ubuntu.com/ubuntu* at 
*http://old-releases.ubuntu.com/ubuntu/*

sudo apt-get update
sudo apt install tesseract-ocr 

As for the beta version, I'll think ...

четверг, 31 мая 2018 г., 10:04:19 UTC+3 пользователь RT-Rakesh написал:
>
> user@computer:~$ sudo apt install tesseract-ocr
> Reading package lists... Done
> Building dependency tree   
> Reading state information... Done
> The following packages were automatically installed and are no longer 
> required:
>   libgnutls-openssl27 postfix-sqlite
> Use 'sudo apt autoremove' to remove them.
> The following additional packages will be installed:
>   libgif7 liblept5 libtesseract-data libtesseract3 tesseract-ocr-eng
>   tesseract-ocr-equ tesseract-ocr-osd
> The following NEW packages will be installed:
>   libgif7 liblept5 libtesseract-data libtesseract3 tesseract-ocr
>   tesseract-ocr-eng tesseract-ocr-equ tesseract-ocr-osd
> 0 upgraded, 8 newly installed, 0 to remove and 180 not upgraded.
> Need to get 945 kB/14.6 MB of archives.
> After this operation, 57.5 MB of additional disk space will be used.
> Do you want to continue? [Y/n] y
> Err:1 http://us.archive.ubuntu.com/ubuntu zesty/main amd64 libgif7 amd64 
> 5.1.4-0.4
>   404  Not Found [IP: 91.189.91.23 80]
> Err:2 http://us.archive.ubuntu.com/ubuntu zesty/universe amd64 liblept5 
> amd64 1.74.1-1
>   404  Not Found [IP: 91.189.91.23 80]
> E: Failed to fetch 
> http://us.archive.ubuntu.com/ubuntu/pool/main/g/giflib/libgif7_5.1.4-0.4_amd64.deb
>   
> 404  Not Found [IP: 91.189.91.23 80]
> E: Failed to fetch 
> http://us.archive.ubuntu.com/ubuntu/pool/universe/l/leptonlib/liblept5_1.74.1-1_amd64.deb
>   
> 404  Not Found [IP: 91.189.91.23 80]
> E: Unable to fetch some archives, maybe run apt-get update or try with 
> --fix-missing?
>
>
> *This is the error being thrown, can some one help me with how to solve 
> this issue. *
>

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/5d45f3de-00a4-44c6-9674-de39c7ea54e4%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Re: [tesseract-ocr] lstmeval gives a perfect result but tesseract fails

[ShreeDevi Kumar]

 >I've trained a LSTM model for a custom language from scratch as explained
here
.

>The language only has about 100 words and 17 characters, so it's pretty
simple.

For such a small model, try to build the legacy version rather than LSTM.

$tesstrain_dir/tesstrain.sh \
   --lang $Lang \
   --exposures "0" \
   --fonts_dir $fonts_dir \
   --fontlist $fonts_for_training \
   --langdata_dir $langdata_dir \
   --tessdata_dir  $tessdata_dir \
   --training_text $langdata_dir/$Lang/$Lang.training_text \
   --output_dir $train_output_dir



ShreeDevi

भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com

On Thu, May 31, 2018 at 3:43 PM, Julien Jemine 
wrote:

> Hi,
>
> I've trained a LSTM model for a custom language from scratch as explained
> here
> .
>
> The language only has about 100 words and 17 characters, so it's pretty
> simple.
>
> When I run lstmeval on my model, I get a perfect match:
> [icm@u16-offcao-07] train1$ lstmeval --model 
> /home/icm/share/tessdata/iqi.traineddata
> --eval_listfile iqitrain2/iqi.training_files.txt --verbosity 2
> Loaded 2/2 pages (1-2) of document /home/icm/train1/iqitrain2/
> iqi.Arial.exp0.lstmf
> Loaded 2/2 pages (1-2) of document /home/icm/train1/iqitrain2/
> iqi.Calibri.exp0.lstmf
> Warning: LSTMTrainer deserialized an LSTMRecognizer!
> Truth:ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> OCR  :ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> Truth:6CUEN 6 CU EN
> OCR  :6CUEN 6 CU EN
> Loaded 2/2 pages (1-2) of document /home/icm/train1/iqitrain2/
> iqi.Lucida_Sans_Typewriter_Semi-Condensed.exp0.lstmf
> Truth:ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> OCR  :ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> Truth:6CUEN 6 CU EN
> OCR  :6CUEN 6 CU EN
> Loaded 2/2 pages (1-2) of document /home/icm/train1/iqitrain2/
> iqi.Verdana.exp0.lstmf
> Truth:ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> OCR  :ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> Truth:6CUEN 6 CU EN
> OCR  :6CUEN 6 CU EN
> Truth:6CUEN 6 CU EN
> OCR  :6CUEN 6 CU EN
> Truth:ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> OCR  :ASTM 10FEEN 10 FE EN 13CUEN 13 CU EN 02B 11 16
> At iteration 0, stage 0, Eval Char error rate=0, Word error rate=0
>
> However, when I put my iqi.traineddata file in my tessdata folder and try
> to run tesseract on the same tif file, I get errors:
> [icm@u16-offcao-07] train1$ tesseract iqitrain2/iqi.training_img.txt
> stdout -l iqi
> Page 0 : /home/icm/train1/iqitrain2/iqi.Arial.exp0.tif
> 6CFN
> 6CUEN 1 CU EN
> Page 1 : /home/icm/train1/iqitrain2/iqi.Calibri.exp0.tif
>
> 6CM 10FEEN 0 6 FEE 13CUEN 11 6 FE EEN 1116
> 6UEN 16 FE
> Page 2 : /home/icm/train1/iqitrain2/iqi.Lucida_Sans_Typewriter_
> Semi-Condensed.exp0.tif
>
> 6TM 13CUEN 13 1 EN 11CUE 11 CU EN 12B 11 16
> 6 6 CU EN
> Page 3 : /home/icm/train1/iqitrain2/iqi.Verdana.exp0.tif
>
> ASTM 103UEEN 13 1CU EN 13CUEN 13 6 FE EEN 11 16
> 6CUEN 6 CU EN
>
>
> Now the really frustrating part: I have the opposite phenomenon with the
> "eng" language! (with eng.traineddata taken from tessdata_best)
> lstmeval gives me a few errors (Eval Char error rate=2.4665552, Word error
> rate=16.67)
> tesseract gives me the right answer! (But the images are generated with
> tesstrain.sh and very common fonts, it's probably to be expected).
>
> Am I doing something wrong?
> What's going on here?
>
> --
> 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 tesseract-ocr+unsubscr...@googlegroups.com.
> To post to this group, send email to tesseract-ocr@googlegroups.com.
> 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/67286720-c624-4239-a812-3c76d7603cf1%
> 40googlegroups.com
> 
> .
> 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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/CAG2NduWCsauX6u4MT4Uzutb0fXAiyg75iwy7x_vf9beAfrhZqw%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Re: [tesseract-ocr] Help for training tesseract to recognize a new (dead) language

[Ramast Magdy]

Impressive! I thought we would need to do a lot of work in order to 
reach that stage??.


The "??" in the text correspond to an unknown character to me, I also 
can't find it among the available unicode characters.

It's certainly 100% not part of the text. Probably indicator of new chapter.
Maybe we could use paragraph sign § symbol for it?

This is very exciting, how do we access the work you have done so far 
and add to it?

Thanks a lot


ⲁⲩⲱ ⲟⲛ ⲁⲓ̈ⲧⲣⲉⲩ ⲣ̄ ⲥⲟⲟⲩ ⲛ̄ ⲉⲃⲟⲧ ⲉⲩⲕⲏⲧ ⲉ ϩⲃⲟⲩⲣ
ⲉⲩⲉⲓⲣⲉ ⲛ̄ ⲛⲉ ϩⲃⲏⲩⲉ ⲛ̄ ⲛⲉⲩⲁⲡⲟⲧⲉⲗⲉⲥⲙⲁ ⲙⲛ̄ ⲛⲉⲩ–
ⲥⲭⲏⲙⲁ ⲧⲏⲣⲟⲩ· ϫⲉ ⲕⲁⲥ ϩⲛ̄ ⲟⲩ ϩⲃⲁ ⲉⲩⲉⲣ̄ ϩⲃⲁ·
ⲁⲩⲱ ϩⲛ̄ ⲟⲩ ⲡⲗⲁⲛⲏ ⲉⲩⲉⲡⲗⲁⲛⲁ ⲛ̄ϭⲓ ⲛ ⲁⲣⲭⲱ̄ ⲉⲧ
ϣⲟⲟⲡ ϩⲛ̄ ⲛ ⲁⲓⲱ̄ ⲁⲩⲱ ϩⲛ̄ ⲛⲉⲩⲥⲫⲁⲓⲣⲁ ⲁⲩⲱ ϩⲛ̄  5
ⲛⲉⲩⲙ̄ⲡⲏⲩⲉ· ⲁⲩⲱ ϩⲛ̄ ⲛⲉⲩⲧⲟⲡⲟⲥ ⲧⲏⲣⲟⲩ· ϫⲉ ⲕⲁⲥ ⲛ̄
ⲛⲉⲩⲛⲟⲓ̈ ⲛ̄ ⲧⲉⲩϭⲓⲛⲙⲟⲟϣⲉ ⲙ̄ⲙⲓⲛ ⲙ̄ⲙⲟ–
?? ⲟⲩ: ⲁⲥϣⲱⲡⲉ ϭⲉ ⲛ̄ⲧⲉⲣⲉ ⲓ̄ⲥ̄ ⲟⲩⲱ ⲉϥϫⲱ ⲛ̄
ⲡⲉⲓ̈ ϣⲁϫⲉ ⲉⲣⲉ ⲫⲓⲗⲓⲡⲡⲟⲥ ϩⲙⲟⲟⲥ ⲉϥⲥϩⲁⲓ̈ ⲛ̄ ϣⲁϫⲉ
ⲗ̄ⲁ̄ ⲁ. ⲛⲓⲙ ⲉⲧ ⲉⲣⲉ ⲓ̄ⲥ̄ ϫⲱ ⲙ̄ⲙⲟⲟⲩ; ⲁⲥϣⲱⲡⲉ ϭⲉ ⲙⲛ̄ⲛ̄ⲥⲁ 10



On 05/31/2018 06:42 AM, ShreeDevi Kumar wrote:
I am attaching the recognition result of the one page image you gave 
from the test model for Coptic I have built. If you can send me the 
correct unicode transcription for that page, I can further fine tune 
it. You can then further modify as per your needs.


--
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/d97ed96e-e701-32c3-aa26-1997a86157b8%40gmail.com.
For more options, visit https://groups.google.com/d/optout.

Re: [tesseract-ocr] Where to find tessdata folder?

[Zdenko Podobny]

Did you follow instruction for installation of that package?
Did you try internet search before posting on forum?
Did you try to search for help in project  tesserocr???

I just put it to google and I got:
https://pypi.org/project/tesserocr/
https://github.com/sirfz/tesserocr
https://oded.blog/2017/01/08/ocr-made-easy-using-tesserocr/

Zdenko


št 31. 5. 2018 o 8:40 Abel Tan  napísal(a):

> Hi,
>
> I installed pytesseract by using Anaconda
>
> conda install -c simonflueckiger tesserocr
>
>
> The path to Anaconda is :C:\Users\Tan\Anaconda3\
>
> The path to tesseract package is :
> C:\Users\Tan\Anaconda3\Lib\site-packages\tesserocr
>
> However when I start up Jupyter notebook and run :
>
> import tesserocr
>
>
> print(tesserocr.image_to_text(image))
>
> I get error:
>
>
> RuntimeError  Traceback (most recent call 
> last) in ()> 1 
> print(tesserocr.image_to_text(imagee))
> tesserocr.pyx in tesserocr._tesserocr.image_to_text()
> RuntimeError: Failed to init API, possibly an invalid tessdata path: 
> C:\Users\Tan\Anaconda3\
>
>
>
>
> How do I solve this problem?
>
>
> Thanks
>
> Abel
>
> --
> 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 tesseract-ocr+unsubscr...@googlegroups.com.
> To post to this group, send email to tesseract-ocr@googlegroups.com.
> 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/11c1f35c-943a-4d9e-a045-71b558dab269%40googlegroups.com
> 
> .
> 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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/CAJbzG8wbVBTVTm-zzqqNdHu8sLvMop5MRAZ_n9qPC%2BiOnP3isg%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

[tesseract-ocr] Not able install tesseract ocr on ubuntu 17.04

[RT-Rakesh]

user@computer:~$ sudo apt install tesseract-ocr
Reading package lists... Done
Building dependency tree   
Reading state information... Done
The following packages were automatically installed and are no longer 
required:
  libgnutls-openssl27 postfix-sqlite
Use 'sudo apt autoremove' to remove them.
The following additional packages will be installed:
  libgif7 liblept5 libtesseract-data libtesseract3 tesseract-ocr-eng
  tesseract-ocr-equ tesseract-ocr-osd
The following NEW packages will be installed:
  libgif7 liblept5 libtesseract-data libtesseract3 tesseract-ocr
  tesseract-ocr-eng tesseract-ocr-equ tesseract-ocr-osd
0 upgraded, 8 newly installed, 0 to remove and 180 not upgraded.
Need to get 945 kB/14.6 MB of archives.
After this operation, 57.5 MB of additional disk space will be used.
Do you want to continue? [Y/n] y
Err:1 http://us.archive.ubuntu.com/ubuntu zesty/main amd64 libgif7 amd64 
5.1.4-0.4
  404  Not Found [IP: 91.189.91.23 80]
Err:2 http://us.archive.ubuntu.com/ubuntu zesty/universe amd64 liblept5 
amd64 1.74.1-1
  404  Not Found [IP: 91.189.91.23 80]
E: Failed to fetch 
http://us.archive.ubuntu.com/ubuntu/pool/main/g/giflib/libgif7_5.1.4-0.4_amd64.deb
  
404  Not Found [IP: 91.189.91.23 80]
E: Failed to fetch 
http://us.archive.ubuntu.com/ubuntu/pool/universe/l/leptonlib/liblept5_1.74.1-1_amd64.deb
  
404  Not Found [IP: 91.189.91.23 80]
E: Unable to fetch some archives, maybe run apt-get update or try with 
--fix-missing?


*This is the error being thrown, can some one help me with how to solve 
this issue. *

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/06faa78f-7a57-4749-9cf2-e9bdce5721c1%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

[tesseract-ocr] Where to find tessdata folder?

[Abel Tan]

Hi,

I installed pytesseract by using Anaconda 

conda install -c simonflueckiger tesserocr


The path to Anaconda is :C:\Users\Tan\Anaconda3\

The path to tesseract package is :
C:\Users\Tan\Anaconda3\Lib\site-packages\tesserocr

However when I start up Jupyter notebook and run :

import tesserocr


print(tesserocr.image_to_text(image))

I get error:


RuntimeError  Traceback (most recent call 
last) in ()> 1 
print(tesserocr.image_to_text(imagee))
tesserocr.pyx in tesserocr._tesserocr.image_to_text()
RuntimeError: Failed to init API, possibly an invalid tessdata path: 
C:\Users\Tan\Anaconda3\




How do I solve this problem?


Thanks

Abel

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/11c1f35c-943a-4d9e-a045-71b558dab269%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

[tesseract-ocr] Training of tesseract

[AKS]

Hi,

I want to use tesseract OCR on images with varying font types and font 
sizes. Also there is a lot of background variations in each images such as 
multi-colored background, background with some designs, illumination 
variance, white background.
If I simply apply  a tesseract with some configuration accroding to my 
requirement, I am not getting very good accuracy.  Also , due to lot of 
variation in background and text writing, I cannot apply some fixed image 
processing on the images before using tesseract.

Can I solve this problem by finetuning tesseract with my set of images?? 

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To post to this group, send email to tesseract-ocr@googlegroups.com.
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/09d3f38a-1eb9-4714-ba6b-01ffbcecb719%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.