You probably need to add something to your LD_LIBRARY_PATH; I think the OpenFST installation instructions talk about this. OpenFST itself is a little tricky to install and configure; this is one of the reasons we have moved OpenFST out of ocropus. (We're generally trying to reduce dependencies from release to release to make installation simpler.)
Note that you do not need OpenFST for building language models; you can do that with the built-in OcroFST class, including saving and loading. OpenFST is only needed for optimizing or transforming language models. Tom On Tue, May 12, 2009 at 11:55, Pierpaolo Monaco <[email protected]>wrote: > I have downloaded and installed the last release of ocropus from the > mercurial repositories. > Everything works pretty well. > > Now I need to work with the language model so I have download and installed > the last version of openfst (v. 1.1) following the installation procedure > from the official website. > > During the compiling and installation process I didn't have any problem but > when i test the shell commands i get this error. > > overco...@overcomer-laptop:~$ fstinfo >> /usr/local/share/ocropus/models/default.fst >> fstinfo: error while loading shared libraries: libfst.so.0: cannot open >> shared object file: No such file or directory >> > > I get this error from any shell command. > > I have this file installed in many directories > > overco...@overcomer-laptop:~$ locate libfst.so.0 >> /home/overcomer/openfst-1.1/src/lib/.libs/libfst.so.0 >> /home/overcomer/openfst-1.1/src/lib/.libs/libfst.so.0.0.0 >> /usr/lib/gnome-vfs-2.0/modules/libfst.so.0 >> /usr/local/lib/libfst.so.0 >> /usr/local/lib/libfst.so.0.0.0 >> > > Because you are experienced in openfst, could somebody tell me what's the > cause? > > thanks. > > 2009/4/15 Thomas Breuel <[email protected]> > > On Tue, Apr 14, 2009 at 05:04, overcomer <[email protected]>wrote: >> >>> Although the image is pretty clear, the text is really "readable", if >>> I process the image with tesseract the result is disappointing. >>> Tesseract recognizes something like the 15 percent of the characters. >>> I think that is depend because of a not-correct use of the dictionary. >>> Now, i can improve this result because the strings are related between >>> them, and some of them are for example just a name of a person or of a >>> city, so with a limited output. >>> What I need to know, if there is some function that analizes the >>> character and return a value that represent the probabilities of the >>> character to be that one, or another one. >> >> >> Yes; OCRopus 0.3 has the ocr-bpnet classifier; OCRopus 0.4 replaces that >> with a new classifier. Both the old and the new classifiers output >> posterior probabilities. >> >> In this way when I will rebuild the string, i can use just this >>> probabilities and other implicit informations of document to improve >>> my results. >> >> >> Yes, not only can you do that, OCRopus supports that directly through its >> use of statistical language models. That is, you can define a statistical >> language model that says something like: >> >> 5.1% London >> 4.9% Paris >> 4.7% New York >> 4.3% Berlin >> ... >> >> If you give OCRopus the input string containing just a city name, you run >> it through its recognizer, and then you apply the statistical language >> model, it will give you the most probable interpretation of the input image. >> >> In 0.3, this process is still a little obscure, in 0.4, you will be able >> to run it directly from the command line. >> >> Tom >> >> >> >> >> > > > -- > ----------------------------- > Pierpaolo Monaco > ---------------------------- > > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
