Hi,
essentially, the next release is already out; just follow the
instructions on the web site:
http://code.google.com/p/ocropus/wiki/InstallTranscript
There will be some more Python scripts (e.g., for other ways of training
the recognizer) and more comments in the Python code.
Documentation and examples will take a little longer, but I hope that
the use of Python already helps.
Tom
On 07.03.2010 03:28, 74yrs old wrote:
Prof.Tom Breuel,
Will you kindly intimate the approximate date on which ocropus likely
to be released and also intimate me the address of website under which
tarbal for download is available.
Hope Tarbal will contain sample datasets of English for benefit of
users and enable me to emulate for Kannada project on the lines of
sample datasets provided by you.
Wishing you All the Best Wishes and Luck,
-sriranga(77yrsold)
On Thu, Mar 4, 2010 at 10:45 AM, 74yrs old <[email protected]
<mailto:[email protected]>> wrote:
Trust it will work in ubuntu 9.04? Hope that tarball will contains
sample datasets of English for hands on experience by the newbies.
On Thu, Mar 4, 2010 at 6:47 AM, Tom Breuel <[email protected]
<mailto:[email protected]>> wrote:
We're preparing for the next release. The release consists of the
following components:
* iulib -- basic image processing
* ocropus -- OCR-specific functionality (libraries and some
command line programs)
* ocroswig -- bindings of iulib and ocropus to Python
* ocropy -- Python library and command line tools
* pyopenfst -- Python bindings of the OpenFST library
Please see the InstallTranscript to see how this is installed.
There is plenty of new functionality:
* all recognition can now be carried out from Python
* there are top-level commands for recognition and training
written in Python
* classifiers now can cope with large character sets
* there are tools for clustering and correcting character
shapes
* there is support for ligatures
* there are numerous bug fixes
* training is possible on very large datasets (many millions of
samples)
We will be calling this release 0.4.4, since there is still some
functionality missing for what we want to call 0.5:
* the Python tools do not yet do a good job at upper/lower case
modeling (but we have good prototype code that just needs to be
integrated)
* the language models need to be tested and improved
* we need to integrate the book-adaptive recognition tools into
the Python code
* Unicode support needs to be integrated into the Python loops
* the main loop of the RAST layout analysis will be
rewritten in
Python
* there will be some new layout analysis that works for
distorted
pages
* we need to integrate our orientation detection and text/image
segmentation code
* we want to get rid of the makefiles
Install instructions are here:
http://code.google.com/p/ocropus/wiki/InstallTranscript
Tom
We'll probably provide a single tarball
--
You received this message because you are subscribed to the
Google Groups "ocropus" group.
To post to this group, send email to [email protected]
<mailto:[email protected]>.
To unsubscribe from this group, send email to
[email protected]
<mailto:ocropus%[email protected]>.
For more options, visit this group at
http://groups.google.com/group/ocropus?hl=en.
--
You received this message because you are subscribed to the Google
Groups "ocropus" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/ocropus?hl=en.
--
You received this message because you are subscribed to the Google Groups
"ocropus" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to
[email protected].
For more options, visit this group at
http://groups.google.com/group/ocropus?hl=en.
