On Thursday, July 30, 2015 at 4:28:53 PM UTC+5:30, Shubham Khandelwal wrote: > > Hello all, > > I am working on text detection problem on any type of images. I used > Tesseract for it. But, in my dataset, there are some images which are not > having texts in it. But on those images, Tesseract is giving some random > texts. > So Could you please suggest me any method/way so that I can improve it by > which It shouldn't detect the texts in non-textual images. > Or if you know any algorithm specially to solve such problems then Please > let me know. > > Thank you very much. >
Check confidence level, it must be low when there are no text -- 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 http://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/69df64e5-9e50-4823-9f83-236deae1e6cd%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
