tesseract-ocr

 conda activate

 conda install -c conda-forge tesseract

    package                    |            build
    ---------------------------|-----------------
    leptonica-1.82.0           |       h950d820_0         2.6 MB  conda-forge
    libarchive-3.5.2           |       hccf745f_1         1.6 MB  conda-forge
    lzo-2.10                   |    h516909a_1000         314 KB  conda-forge
    tesseract-5.0.1            |       h84e3e21_0       171.4 MB  conda-forge
    ------------------------------------------------------------
                                           Total:       175.9 MB

tesseract

Usage:
  tesseract --help | --help-extra | --version
  tesseract --list-langs
  tesseract imagename outputbase [options...] [configfile...]

OCR options:
  -l LANG[+LANG]        Specify language(s) used for OCR.
NOTE: These options must occur before any configfile.

Single options:
  --help                Show this help message.
  --help-extra          Show extra help for advanced users.
  --version             Show version information.
  --list-langs          List available languages for tesseract engine.

example 

wget https://tesseract-ocr.github.io/tessdoc/images/eurotext.png

 

 tesseract eurotext.png eurotext-eng

cat eurotext-eng

eurotext-eng.txt  eurotext.png      
(base) [[email protected] ~]$ cat eurotext-eng.txt
The (quick) [brown] {fox} jumps!
Over the $43,456.78 <lazy> #90 dog
& duck/goose, as 12.5% of E-mail
from [email protected] is spam.
Der ,.schnelle” braune Fuchs springt
tiber den faulen Hund. Le renard brun
«rapide» saute par-dessus le chien
paresseux. La volpe marrone rapida
salta sopra il cane pigro. El zorro
marron rapido salta sobre el perro
perezoso. A raposa marrom rapida
salta sobre 0 cao preguigoso.

 

TESSDATA_PREFIX environment variable

tesseract testing/eurotext.tif testing/eurotext-eng -l eng

tesseract testing/eurotext.png testing/eurotext-engdeu -l eng+deu

 tesseract testing/bilingual.jpg testing/bilingual-enghin -l eng+hin

 tesseract testing/bilingual.jpg testing/bilingual-hineng -l hin+eng

OUTPUTS
 

searchable pdf output:: 

tesseract testing/eurotext.png testing/eurotext-eng -l eng pdf

pdf+txt layer

tesseract c:\temp\test_ara.jpg -l ara -psm 3 c:\temp\test_ara pdf 

Hocr output

tesseract testing/eurotext.png testing/eurotext-eng -l eng hocr

cat eurotext-eng.hocr 

tsv output

tesseract testing/eurotext.png testing/eurotext-eng -l eng tsv    

page segmentation

tesseract  testing/san002.png testing/san002-psm6 -l san -psm 6 

tesseract testing/san002.png testing/san002-psm3 -l san -psm 3

src:: 

https://anaconda.org/conda-forge/tesseract

https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html 

https://github.com/tesseract-ocr/