Inference for Optical Character Recognition

API for Optical Character Recognition.

In combination with an API for Object Detection it can be used e.g. for Document Layout Analysis.

Prerequisites:

• docker
• docker-compose

Check for prerequisites

To check if docker-ce is installed:

docker --version

To check if docker-compose is installed:

docker-compose --version

Install prerequisites

Ubuntu

To install Docker and Docker Compose on Ubuntu, please follow the link.

Windows 10

To install Docker on Windows, please follow the link.

Build The Docker Image

In order to build the project run the following command from the project's root directory:

sudo docker-compose up --build

API Endpoint

To see the available endpoint, open your favorite browser and navigate to:

http://<machine_IP>:5001/docs

You can change the port in the docker compose file.

Also you can test the endpoint with image files from the test directory.

/optical_character_recognition (POST)

This endpoint performs inference on specified language and uploaded image and returns extracted text: