MichalBusta / DeepTextSpotter

285 stars 101 forks source link

Single Characters are not recognized #49

Closed mowkee closed 6 years ago

mowkee commented 6 years ago

Is it possible to detect single characters? for example the word " T Segments" the word "Segments" is recognized but "T" is not (There is more than single space between "T" and "Segments"). A bounding box is drawn around it though but it won't appear on the std out like the "Segments" word. Is it possible to change this behavior?

Gitchenguang commented 6 years ago

I changed the codes For process_splits in utils.py line 288: if len(text) > 2 and ( text.isdigit() or is_dict): --> if len(text) > 0 and ( text.isdigit() or is_dict): For demo.py line 164: if len(det_text) < 3 and mean_conf < 0.8: --> if len(det_text) < 1 and mean_conf < 0.8: and it will appear now

mowkee commented 6 years ago

Yeah I dug deep and found it myself but forgot to come and update here. You beat me to it. I confirm that this solution works incase anyone is interested in the future.