Total Text Does not give character level annotation

Question

Total Text Does not give character level annotation

anmol4210 opened this issue 5 years ago · 3 comments

my bad

Answer 1 · 2019-09-06T05:48:52.000Z

Hi,
Total text gives character level mask but it does not gives coordinates of every character in the image. But you have mentioned character level annotation as yes.

Answer 2 · 2019-09-11T09:23:05.000Z

Thank you for your comment.

Since Total-text dataset provides character-level mask, we can use connected component analysis (CCA) to obtain the coordinates of every character based on the character-level mask.

By the way, I think it would be more appropriate to say pixel-level annotation as yes.