toolkit for building OCR systems
The Gamera OCR Toolkit is meant to help building optical character
recognition (OCR) systems for standard text documents. Even though it can
be used as is, it is specifically designed to make individual steps of the
recognition system customizable and replaceable. It provides:
* a flexible mechanism for plugging in custom page segmentation algorithms
* heuristic rules for dealing with diacritics, and for disambiguation of
common confused roman characters (like comma and apostrophe, or lower
and upper case ‘W’)
* a ready-to-run script ocr4gamera which acts as a basic OCR-system.
Note that the toolkit does not include any training data.
OCR Toolkit for Gamera
"Optical character recognition" (OCR) means the extraction of the
text content from a document image.
This toolkit provides
- python library functions for building custom ocr applications
- a ready to use script ocr4gamera
This toolkit has been written for the Gamera framework and req
ocr4gamera - OCR system using the Gamera framework
ocr4gamera -x <traindata> [options] <imagefile>
-v <int>, --verbosity=<int>
Set verbosity level to <int>. Possible values are 0
(default): silent operation; 1: information on
ocr4gamera (1.0.6-3) unstable; urgency=low
* Don't include *.egg-info in the binary package, as distribution name is
* Do not pass explicit debian/control path to pyversions.
-- Jakub Wilk <email@example.com> Tue, 19 Jun 2012 14:11:39 +0200
ocr4gamera (1.0.6-2) unstable; urgency=low
* Upload to unstable.
* Add lintian override for build-depends-on-python-dev-with-no-a
Changelog of the OCR Toolkit for Gamera
Version 1.0.6, Feb
Browse inside python-gamera.toolkits.ocr_1.0.6-3_all.deb
Results 1 - 1 of 1Search over 15 billion files
© 1997-2016 FileWatcher.com