Optical Character Recognition (OCR) with OpenVINO™

In this tutorial optical character recognition is presented. This notebook is a continuation of hello-detection notebook.

Notebook Contents

In addition to previously used horizontal-text-detection-0001 model, atext-recognition-resnet model is used. This model reads tight aligned crop with detected text converted to a grayscale image and returns tensor that is easily decoded to predicted text. Both models are from Open Model Zoo.

Installation Instructions

This is a self-contained example that relies solely on its own code.
We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. For details, please refer to Installation Guide.