I'm doing an OCR, I already tried everything in console and it's fine. Now I am doing the visual part, in that I am a newbie and I do not have much experience, so any help is welcome, I am working with python and I have doubts on how to do the image segmentation part. I am supposed to show an image with the predicted segmentation,like this. But if the user wants to modify it, he should be able to do so: Add a new box or delete and edit one already created. Like this

But I don't have the slightest idea how to start with the UI, any recommendations? Please

CodePudding user response：

I use annotorious and it was perfect for what I needed

CodePudding user response：

FWIW there's also a Jupyter widget built around Annotorious, in case you want (or need) to stick with Python:

https://github.com/fcollonval/ipannotoryous