Resources:
https://nanonets.com/blog/receipt-ocr/#why-is-it-a-difficult-problem
https://www.tensorflow.org/tutorials/text/text_classification_rnn
https://www.tensorflow.org/tutorials/images/cnn
https://www.raywenderlich.com/
https://www.geeksforgeeks.org/os-module-python-examples/
https://stackoverflow.com/questions/764631/how-to-hide-console-window-in-python
Kaggle.com
find this about reading receipts with opencv on kaggle:
part 1: https://www.kaggle.com/dmitryyemelyanov/receipt-ocr-part-1-image-segmentation-by-opencv
part 2: https://www.kaggle.com/dmitryyemelyanov/receipt-ocr-part-2-text-recognition-by-tesseract
2d39bc2394fd9508f12966bd7ddd1fba7506ab98
Premade models using EAST:
https://github.com/argman/EAST
https://www.pyimagesearch.com/2018/08/20/opencv-text-detection-east-text-detector/