Optical Character Recognition OCR

From WickyWiki
Revision as of 08:18, 31 August 2022 by Wilbert (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)


Tesseract OCR

Source code, info and links:

Binaries, installers:

Commandline usage:

tesseract imagename outputbase [-l lang] [--oem ocrenginemode] [--psm pagesegmode] [configfiles...]

Greenshot integration

This will create a .txt -file in addition to the created image-file with OCR results. Feel free to change any parameters to improve the results.

Greenshot screen capture:

Go to Greenshot > Preferences > Plugins > External command plugin > Configure > New

 Name: Tesseract-OCR
 Command: C:\Program Files\Tesseract-OCR\tesseract.exe 
 Arguments "{0}" "{0}" -c paragraph_text_based=0 -l eng+nld --psm 6

Go to Greenshot > Preferences > Destination

 Select "Save directly" and "Tesseract-OCR"