You can try a local-otsu preprocessing step on this image and then pass the binary image to Tesseract. If you need something more sophisticated, try colour invariant text-binarization (https://github.com/jasonlfunk/ocr-text-extraction) instead of local-otsu.
On Saturday, June 9, 2018 at 12:47:08 PM UTC+5:30, [email protected] wrote: > > Hi All, > > > I have this image and I want to recognize the letters inside it. How I can > to that. > > > I have tried to change the background to white and text to black but > failed also. > > > <https://lh3.googleusercontent.com/-5OOCNljvGh4/WxsDNJG97OI/AAAAAAAAANM/pe4YI57WIn4WDhu7iUlfND1pNiMxmGeOACLcBGAs/s1600/img2.png> > > -- 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/aea69544-4871-44f8-9395-3eb149892906%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
