Haha, you can also try -c tessedit_char_whitelist='我愛你', single
quote instead of double quote.
--
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+uns
maybe you can try '-c tessedit_char_whitelist="我愛你"', something like this.
un C 于2020年7月29日周三 下午5:27写道：
> I am using tesseract v5.0.0-alpha.20200328.
>
> I tried ' -c tessedit_char_whitelist=0123456789,' it does work.
> But for Chinese characters, neither '-c tessedit_char_whitelist=我愛你' nor
> t
It work!! Thanks!
在 2019年4月4日星期四 UTC+8下午1:39:25，shree写道：
>
> Try
>
> tesseract test.jpg test --psm 6 lstm.train
>
>
--
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 emai
I have an image, I run tesseract on it, can recognise the fist line
although some wrong word.
But I run `tesseract test.jpg test lstm.train' to make lstf file. It can't
recognise the first line. The log is:
```
No block overlapping textline: The first line content
```
How can I improve this. T
I have a image like this:
[image: 111.jpg]
And I then run
tesseract 111.jpg out -l chi_sim; cat out.txt;rm out.txt;
But the result is
Tesseract Open Source OCR Engine v4.0.0-332-gb727 with Leptonica
E
I have no idea how to improve this. Any ideas? Thank you.
--
You received this message be
rated traineddata with and without recoder
> option.
>
>
> On Tue, Mar 12, 2019 at 9:59 PM 童虎 >
> wrote:
>
>> I use this command follow by a post to create a xx.tessdata
>>
>> combine_lang_model \
>> --input_unicharset cp.unicharset \
>> --script_dir
I want train on 4.0 version
I use
unicharset_extractor 0_gray.box
to create the unicharset file.
and use
combine_lang_model \
--input_unicharset unicharset \
--script_dir /Users/th/source/langdata \
--output_dir . \
--lang chi_sim
to create the chi_sim.traineddata file
and train use this co
I use this command follow by a post to create a xx.tessdata
combine_lang_model \
--input_unicharset cp.unicharset \
--script_dir /Users/th/source/langdata \
--output_dir output \
--pass_through_recoder \
--lang cp
and the cp.unicharset is very simple：
https://gist.github.com/huhuang03/62391f632d
👌, thank you!
在 2018年12月24日星期一 UTC+8上午1:50:47，Seokbong Choi写道：
>
> Use HSV filter. You can use OpenCV. I guess you don't need to filter out V
> range, but High S range may work.
>
>
> On Sun, Dec 23, 2018 at 10:09 AM 童虎 >
> wrote:
>
>>
>> I wa
I want use tessract to extra green text(which is Chinese word)
[image: t_first_name_more_foggy.png]
but the result it not well.
And I save the `-c tessedit_wite_images=1` to see the middle image, which
is not well
[image: bb.png]
How can I preprocess this picture? I'm new to image process.
10 matches
Mail list logo
