2017-02-24 07:39:35 +00:00
|
|
|
# tesseract
|
|
|
|
|
|
|
|
|
|
> OCR (Optical Character Recognition) engine.
|
2019-06-03 01:06:36 +01:00
|
|
|
> More information: <https://github.com/tesseract-ocr/tesseract>.
|
2017-02-24 07:39:35 +00:00
|
|
|
|
2021-01-31 17:05:18 +00:00
|
|
|
- Recognize text in an image and save it to `output.txt` (the `.txt` extension is added automatically):
|
2017-02-24 07:39:35 +00:00
|
|
|
|
|
|
|
|
`tesseract {{image.png}} {{output}}`
|
|
|
|
|
|
|
|
|
|
- Specify a custom language (default is English) with an ISO 639-2 code (e.g. deu = Deutsch = German):
|
|
|
|
|
|
|
|
|
|
`tesseract -l deu {{image.png}} {{output}}`
|
|
|
|
|
|
|
|
|
|
- List the ISO 639-2 codes of available languages:
|
|
|
|
|
|
|
|
|
|
`tesseract --list-langs`
|
|
|
|
|
|
|
|
|
|
- Specify a custom page segmentation mode (default is 3):
|
|
|
|
|
|
|
|
|
|
`tesseract -psm {{0_to_10}} {{image.png}} {{output}}`
|
|
|
|
|
|
|
|
|
|
- List page segmentation modes and their descriptions:
|
|
|
|
|
|
|
|
|
|
`tesseract --help-psm`
|
