 |
 |
In this tutorial optical character recognition is presented. This notebook is a continuation of 004-hello-detection notebook.
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.
If you have not installed all required dependencies, follow the Installation Guide.