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.
