search

MhLiao / DB

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
2.08k stars 476 forks source link

How can I generate or obtain the visualization result for predicted characters? #28

Closed Peony-Wang closed 4 years ago

Peony-Wang commented 4 years ago

Hi Minghui, thanks for your awesome work!

I found that adding --visulize after the evaluation command will generate the visualization results for only the threshold map. I'm wondering how can I generate or obtain the visualization result for predicted characters?

Thank you!

MhLiao commented 4 years ago

@Peony-Wang What's the meaning of predicted characters? Do you mean the recognition results? This repo is only a scene text detector which produces bounding boxes of the text instances.

Peony-Wang commented 4 years ago

@Peony-Wang What's the meaning of predicted characters? Do you mean the recognition results? This repo is only a scene text detector which produces bounding boxes of the text instances.

Got it. Thanks for your reply! I have one more question, could you give a clue bout how to combine your work with other detection+recognition work to improve the result of the recognition result?

MhLiao commented 4 years ago

@Peony-Wang Once you get the detection results of our method, you can crop the text regions for recognition (eg. CRNN or ASTER).

Peony-Wang commented 4 years ago

Thank you for your answer！