Skip to content

licence-plate-detection

Description

Note

More information about the service specification can be found in the Core concepts > Service documentation.

This service performs automatic license plate detection on one or more input images using a YOLOv8 model that you provide.

The API expects one or more images as input and returns, for each image:

  • a list of detected license plates with bounding boxes
  • the confidence score of each detection
  • the crop of the detected plate image (base64 encoded)

The API documentation is automatically generated by FastAPI using the OpenAPI standard. A user-friendly interface is available under the /docs route, where the endpoints are described.

Usage

Input

The /compute endpoint accepts a set of input images. Each image should be provided as base64 data.

Output

For each input image, the service returns:

  • bounding box coordinates of plates,
  • confidence values,
  • class label (e.g., “license_plate”),
  • cropped plate images (base64 encoded),
  • summary per image.

Request and response formats are visible in the auto-generated API docs at the /docs route.

Environment variables

Check the Core concepts > Service > Environment variables documentation for more details, including how to configure ports, hostnames, and other settings.

Run the tests with Python

Check the Core concepts > Service > Run the tests with Python documentation for instructions on running local tests against this service.

Start the service locally

Check the Core concepts > Service > Start the service locally documentation for more details on starting the service locally with Docker Compose or plain Python.