see icon indicating copy to clipboard operation
see copied to clipboard

Text Recognition on new dataset

Open SiDinhThoi opened this issue 5 years ago • 4 comments

Hi @Bartzi,

I am wondering about do your algorithm can work on following images?

0000000_orig 0000001_orig 0000002_orig

Thank you and looking forward to hearing back from you!

SiDinhThoi avatar Apr 15 '19 14:04 SiDinhThoi

Hmm, I don't think it would work well... you see one of the problems with the approach is that it is currently not really possible to work with images that contain lots of text and also text that is in very different positions... But actually you should not need to have such a complicated deep learning system for localizing and detecting such text...

Bartzi avatar Apr 15 '19 15:04 Bartzi

Hi @Bartzi,

Thank you for your response

I am curious about if I train the model from scratch with this new dataset, will it work? or do you have any idea to make the algorithm can work with this new dataset?

Sincerely,

Si

SiDinhThoi avatar Apr 15 '19 16:04 SiDinhThoi

As I said, I don't think it will work out of the box, as the proposed system has problems with many textlines in large position variations. The guidance obtained by the localization network from the recognition network is not enough for such problems, but all in all I think you are still better off with a standard print OCR engine, for such data...

Bartzi avatar Apr 23 '19 09:04 Bartzi

Thank you for your advice @Bartzi

SiDinhThoi avatar Apr 23 '19 14:04 SiDinhThoi