Hi Rajamani The issue you might be facing is that Tesseract Reads text for the Fonts it is trained for. The K in kellogs is not in a proper format which can't be read by Tesseract.
Hope this helps. Regards Adarsh SHUKLA On Monday, February 26, 2018 at 9:03:32 PM UTC+5:30, Rajamani Giridharan wrote: > > Hi, > Tesseract Version 3.04.01 is unable to read cursive text from the product > labels (image/photos) like Kelloggs, Nivea, etc. > > The tesseract code downloaded from github is returning 'null' results. I > tried changing the size of the image and also increased the resolution,but > none of them is returning the result. > Also I tried pre-processing using OpenCV libraries, but the results are > none. > > Kindly help. I have attached a sample input file for the text extraction. > > Thanks and Regards, > > Giridharan R > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To post to this group, send email to tesseract-ocr@googlegroups.com. 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/71426218-9ed1-4989-9137-bfa857645570%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
