DOKK / manpages / debian 12 / tesseract-ocr / classifier_tester.1.en
CLASSIFIER_TESTER(1)   CLASSIFIER_TESTER(1)

classifier_tester - for *legacy tesseract* engine.

classifier_tester -U unicharset_file -F font_properties_file -X xheights_file -classifier x -lang lang [-output_trainer trainer] *.tr

classifier_tester(1) runs Tesseract in a special mode. It takes a list of .tr files and tests a character classifier on data as formatted for training, but it doesn’t have to be the same as the training data.

a list of .tr files

-l lang

(Input) three character language code; default value eng.

-classifier x

(Input) One of "pruner", "full".

-U unicharset

(Input) The unicharset for the language.

-F font_properties_file

(Input) font properties file, each line is of the following form, where each field other than the font name is 0 or 1: 

*font_name* *italic* *bold* *fixed_pitch* *serif* *fraktur*

-X xheights_file

(Input) x heights file, each line is of the following form, where xheight is calculated as the pixel x height of a character drawn at 32pt on 300 dpi. [ That is, if base x height + ascenders + descenders = 133, how much is x height? ] 

*font_name* *xheight*

-output_trainer trainer

(Output, Optional) Filename for output trainer.

tesseract(1)

Copyright (C) 2012 Google, Inc. Licensed under the Apache License, Version 2.0

The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985-1995) and Google (2006-present).

01/11/2023