2009/3/11 Indu s <[email protected]> > Hii Debayanin > > I tried the tesseract trainer uploaded by you from the following link > > > http://code.google.com/p/tesseractindic/source/browse/trunk/tesseract_trainer/
Try http://tesseractindic.googlecode.com/files/tesseract_trainer.beta.tar.gzinstead. I have not committed my latest work yet. The lan wire in my room got severed. > > > but for that image box file generated by tesseract seems to be incorrect it > doesnt match > with the box file output by your program > ৫ 0 0 80 60 > ৬ 120 0 200 60 Yes this is a problem which i overlooked, but have now been able to solve. It appears that the ImageDraw.getbbox() function only works on images with a black background and white foreground. I am making appropriate changes. Will commit and inform soon. > > > this what the program outputs but if we give the same image to tesseract to > make box file the generated box file appears like this > > 2 2 11 70 42 > E 362 10 448 41 > @ 723 10 775 42 Also, I changed my approach of generating strips to generating one image per symbol so that erroneous symbols during training can be tracked and dealt with separately. Just hang on for my next commit. -- Be Intelligent, Use GNU/Linux http://debayanin.googlepages.com/ http://debayan.wordpress.com http://lug.nitdgp.ac.in --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
