Hello, I am experiencing very similar issues, have everyone found a workaround for this ?
On Monday, November 30, 2009 at 2:44:53 PM UTC+1, Patrick Questembert wrote: > > Indeed - I am experiencing illegal box coordinates in about 40% of the > images I scan (I am using Tesseract 3.0). You can find such an example > on: > http://www.scanbizcards.com/IMG_0735.JPG > and the resulting boxes (after reducing image size by 2 along X and Y > dimension) on: > http://www.scanbizcards.com/IMG_0735-boxes.JPG > > As you can see, the bottom wide box cuts a phone number in two near > the top of the box. This is because the box returned is: > [left=0,top=338,width=1024,height=351]. If you trust the "top" value > of the box, and substract the height minus one (351-1) from it to > compute y0, you will get precisely -12 as Eugene mentioned. > > I just switched my code to trust the height instead, which avoids > getting a negative value for y0. This gets me a higher y1=350 > (essentially setting y0=0 and top=height-1) which by the way cuts the > phone number less but still a bit so I think I am still not getting > the correct values. > > Patrick > > On Nov 30, 1:14 am, Eugene Reimer <[email protected]> wrote: > > Nope - that part is perfectly clear, and obvious to all concerned I'm > > sure - at least it is to me. > > > > Ray Smith wrote, On 2009-11-29 23:17: > > > > > Sounds like a mixup with topdown vs bottomup coordinates. The > > > tesseract coordinates have the origin at the bottom-left. > > > > > Ray. > > > > >> On Nov 28, 2009 7:40 PM, "Eugene Reimer" <[email protected] > > >> <mailto:[email protected]>> wrote: > > > > >> Both your experiences sound like variations of the issue I reported > for > > >> version 2.03, and again for 2.04. See my email from 2009-07-23 > 05:15, > > >> and the "issue" report: > > >> http://code.google.com/p/tesseract-ocr/issues/detail?id=223 > > > > >> In my examples the box-coordinates had sensible X-values, but the > > >> Y-coordinates were either correct or too low by some 12-pixels. From > > >> your reports, there are also other kinds of X-Y errors. > > > > >> wdingus wrote, On 2009-11-28 21:15: > > > > >> >Agreed... I was just about to post about this and went looking to > > >> see >if anyone else had reported... > > > > > -- > > > > > You received this message because you are subscribed to the Google > > > Groups "tesseract-ocr" group. > > > To post to this group, send email to [email protected] > <javascript:>. > > > To unsubscribe from this group, send email to > > > [email protected] <javascript:>. > > > For more options, visit this group at > > >http://groups.google.com/group/tesseract-ocr?hl=en. > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/b50ec1fb-1f48-4803-9f2d-c56f49420d83%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
