On Thu, Jul 28, 2011 at 12:16 PM, Sandeep Parmar < [email protected]> wrote:
> Hi Zdenko, > > these results are very much similar to the one which i got using older > version(tesseract 3.0) but with 3.01 it was coming worst. > > Can you share your 3.01 exe files for training? I am using Windows XP 32 > bit. I will cross check it with the same input image and > see whether i am able to get the similar results as yours. > > First of all: 3.01 training is not documented so I suggest to use it only for testing purposes (testers/hacker are welcomed ;-) ) My build can be sound here [1] (build with VS 2008 on Windows XP SP3). I just compress with upx to get smalled exe Zdenko [1] https://github.com/zdenop/qt-box-editor/downloads Thanks > Sandeep > > > On Thu, Jul 28, 2011 at 3:36 PM, zdenko podobny <[email protected]> wrote: > >> I run (svn r596) on Windows XP: >> "tesseract eng.arial.tif eng.arial.301 batch.nochop makebox" >> and I got totally different result (see attachment). I also tried 3.00 and >> it gave me similar result as r596 (yes there are differences). >> What OS you use? >> >> Zdenko >> >> On Thu, Jul 28, 2011 at 10:11 AM, Sandeep Parmar < >> [email protected]> wrote: >> >>> hi zdenko/sriranga, >>> >>> please find the zipped folder attached here with. >>> >>> sandeep >>> >>> >>> On Thu, Jul 28, 2011 at 1:19 PM, Sriranga(78yrsold) < >>> [email protected]> wrote: >>> >>>> @Sandeep, >>>> As suggested by Zdenko Podobny, please forward sample images with its >>>> box files? >>>> >>>> >>>> On Thu, Jul 28, 2011 at 1:08 PM, zdenko podobny <[email protected]>wrote: >>>> >>>>> As always - can you please send example image + box file? >>>>> >>>>> Zdenko >>>>> >>>>> >>>>> On Thu, Jul 28, 2011 at 9:26 AM, Sandeep Parmar < >>>>> [email protected]> wrote: >>>>> >>>>>> Hi, >>>>>> I am using English language fonts like 'Comic sans MS', >>>>>> 'Times','Arial' etc. >>>>>> >>>>>> >>>>>> On Thu, Jul 28, 2011 at 12:50 PM, Sriranga(78yrsold) < >>>>>> [email protected]> wrote: >>>>>> >>>>>>> Sandee >>>>>>> which lang you are using for training purpose since you are using >>>>>>> cowboxer? >>>>>>> >>>>>>> >>>>>>> On Thu, Jul 28, 2011 at 12:26 PM, Sandeep Parmar < >>>>>>> [email protected]> wrote: >>>>>>> >>>>>>>> Hello Everyone, >>>>>>>> >>>>>>>> I downloaded the latest tesseract 3.01 from the svn and was trying >>>>>>>> to train the tesseract for new fonts. >>>>>>>> >>>>>>>> I created the box files by following the command >>>>>>>> "tesseract [lang].[fontname].exp[num].tif [lang].[fontname].exp[num >>>>>>>> ] -l yournewlanguage batch.nochop makebox " >>>>>>>> given on training page of tesseract wiki. >>>>>>>> >>>>>>>> But when I saw the box file in Cowboxer, It was showing wrong value >>>>>>>> for almost all the characters of the image. >>>>>>>> >>>>>>>> I am not able to figure out what could be the reason for this as >>>>>>>> this is not the first time that I am training tesseract, >>>>>>>> I have succesfully trained Tesseract3.00 for new fonts already. But >>>>>>>> on Training Tesseract 3.01 I got the above problem in Box files >>>>>>>> genereated. >>>>>>>> >>>>>>>> Please Help. >>>>>>>> >>>>>>>> Thanks and Regards >>>>>>>> Sandeep >>>>>>>> >>>>>>>> >>>>>>>> -- >>>>>>>> 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] >>>>>>>> To unsubscribe from this group, send email to >>>>>>>> [email protected] >>>>>>>> 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 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/tesseract-ocr?hl=en >>>>>>> >>>>>> >>>>>> -- >>>>>> 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] >>>>>> To unsubscribe from this group, send email to >>>>>> [email protected] >>>>>> 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 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/tesseract-ocr?hl=en >>>>> >>>> >>>> -- >>>> 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] >>>> To unsubscribe from this group, send email to >>>> [email protected] >>>> 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 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/tesseract-ocr?hl=en >>> >> >> -- >> 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] >> To unsubscribe from this group, send email to >> [email protected] >> 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 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/tesseract-ocr?hl=en > -- 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] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en
