I'm trying to achieve algorithm that will extract text from few areas(marked with red color) on label(similar to attached image) and QR code on a single photo taken with mobile camera so label may be in a little bit different position. I'm struggling with choosing and executing good enough solution to accomplish it. I was wondering about labeling images with marked boxes around my area of intersts and then put it into some CNN. I've encounter some interesting paper on text spotting(https://arxiv.org/pdf/1810.12738v1.pdf) but I'm not sure if it would be good solution for my problem.
I will be more than thankful for any help and suggestions. Thanks in advance :)