Thanks. There's nothing wrong in principle with those inputs (the text is obviously nice and clean). However, this kind of input is not what OCRopus is currently trained or tested on (neither is Tesseract, which also gives fairly noisy output).
OCRopus should work better on them in 0.5, after it has been trained on more kinds of inputs. Tom On Wed, Jul 1, 2009 at 20:52, zhi<[email protected]> wrote: > > submitted, hope it can help in someway. > > Thanks > > On Jul 1, 2:40 pm, Thomas Breuel <[email protected]> wrote: >> Can you submit an issue report on ocropus.org and attach the image, please? >> >> Based on that, we can determine whether it's an actual problem, or >> simply a document type that OCRopus isn't trained to recognize yet. >> We can then prioritize it accordingly. >> >> "Beam search failed" simply means one of two things. Either something >> went wrong with the segmentation of the input line, or there was no >> reasonable way for OCRopus to recognize it using its current models. >> >> Tom >> >> On Wed, Jul 1, 2009 at 17:51, zhi<[email protected]> wrote: >> >> > Hi guys, >> >> > After no lucking trying to install Ocropus on my Centos box, I now >> > followed closely and successfully installed it on my ubunbu 9.04. I >> > tested about 10 images and none of them seems to work. I copied some >> > of output and hope someone can help me out. >> >> > I got >> >> > t...@ubuntu:~/ocrtest$ ocropus page 32047.png >> > Ag3A >> > For a quota0on >> > 0oca'I: 1890 6i7 6i7 >> > Exis'ng Cutome's >> > tocan: 1890 618 618 >> > [beam search failed] >> > [beam search failed] >> > [beam search failed] >> > [beam search failed] >> > [beam search failed] >> >> > t...@ubuntu:~/ocrtest$ ocropus page LimeDaleybusinesscard.png >> > Jon Daley >> > 131 Denny Road >> > Uaencia, PA 1 6059 >> > jon4imedaleycom >> > 412-360m844 >> > 'yyrme wv imedaleycom >> > [info] WARNING: feature extraction failed [28]: CHECK ocr-line/ >> > linerec.cc:350 b.height()<pgetf("maxheight") >> > [beam search failed] >> > . Embedded Sob8re >> > . System Design >> > . Testing Automation >> > . FTP and Web Hosting >> > . Personal Technical Support >> > . High'y Customized Solutions >> > . Industrial Controls . Individuals to Medium-Sized Businesses >> > terminate called after throwing an instance of 'glinerec::BadTextLine' >> > Aborted >> >> > t...@ubuntu:~/ocrtest$ ocropus page LimeDaleybusinesscard.png >> > Jon Daley >> > 131 Denny Road >> > Uaencia, PA 1 6059 >> > jon4imedaleycom >> > 412-360m844 >> > 'yyrme wv imedaleycom >> > [info] WARNING: feature extraction failed [28]: CHECK ocr-line/ >> > linerec.cc:350 b.height()<pgetf("maxheight") >> > [beam search failed] >> > . Embedded Sob8re >> > . System Design >> > . Testing Automation >> > . FTP and Web Hosting >> > . Personal Technical Support >> > . High'y Customized Solutions >> > . Industrial Controls . Individuals to Medium-Sized Businesses >> > terminate called after throwing an instance of 'glinerec::BadTextLine' >> > Aborted > > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
