The preferred format is PNG; there is no support for reading JPEG2000
images.

The Mercurial version of OCRopus has largely moved to Python
toplevels; however, it still uses the OCRopus image I/O routines
because they actually work better than PIL or other Python
libraries.

It wouldn't be too hard to modify the code to read JPEG2000 images;
however, I just recommend batch-converting to PNG.  Given that OCRopus
is already a multi-stage command line process, that shouldn't really
change things too much.

Tom

On Dec 19, 12:44 am, Benjamin Lambert <[email protected]> wrote:
> Hi all,
>
> I've been having success getting everything working, and testing it
> out.  One quick question: is OCR from JPEG2000 images supported?  I
> tried to run "ocropus-pages" on some *.j2k images, which reported an
> error that the extension ".j2k" is not recognized.  Is it a problem
> with the file format or the extension?  If the file-format, then I
> should convert it another format?  Is anything in particular
> preferred? PNG?
>
> Best,
> Ben
>
> --
> Benjamin Lambert
> Ph.D. Student of Computer Science
> Carnegie Mellon Universitywww.cs.cmu.edu/~belamber

-- 
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.

Reply via email to