Manual Installation Steps

Follow the steps below to manually install USDOT OCR On-premises with Docker.

danger

For the commands below, make sure to replace YOUR_LICENSE_KEY with your License Key and YOUR_API_TOKEN with your API Token. Get your token and license key. Use On-premises Licenses.

List of Docker Images

The Docker image is available for linux/amd64 architecture. The image structure is:

platerecognizer/usdot:<version>

• <version>: leave blank for latest.
• To see the list of tags, select the USDOT image from Docker Hub and then click "Tags".

Examples:

• Specific version: platerecognizer/usdot:0.1.4
• Latest version: platerecognizer/usdot:latest or platerecognizer/usdot

Installation

Installation on an Intel CPU

Abbreviated installation steps below. For a detailed, step-by-step guide, see the Install Docker and SDK on Windows and the associated FAQ.

1. Sign up and log in.
2. Subscribe to a USDOT OCR On Premise plan.
3. Install Docker on your local machine. See requirements.
4. Get our On-premises image:

   docker pull platerecognizer/usdot

5. Install and run the Docker container:

   docker run --restart="unless-stopped" \
     -t \
     -p 8001:8001 \
     -v license:/license \
     -e TOKEN=YOUR_API_TOKEN \
     -e LICENSE_KEY=YOUR_LICENSE_KEY \
     platerecognizer/usdot

---

Testing the API

Once the container is running, you can test it by sending a sample image.

Linux

# Get a sample picture
curl -o /tmp/usdot.jpg https://app.platerecognizer.com/static/usdot_demo.jpg

# Read USDOT information
curl -F 'image=@/tmp/usdot.jpg' http://localhost:8001/predict/

Windows

# Get a sample picture
curl -o usdot.jpg https://app.platerecognizer.com/static/usdot_demo.jpg

# Read USDOT information
curl -F "image=@usdot.jpg" http://localhost:8001/predict/

If successful, you will receive a JSON response with the extracted DOT number and details. See the output format documentation.

---

Consuming the API

The On-premises app also exposes Swagger UI at:

http://localhost:8001/docs

From Swagger UI, you can explore endpoints, test parameters, and review available fields.

Example with Parameters

cURL

curl -F 'image=@usdot.jpg' -F 'min_detection_score=0.2' -F 'min_ocr_score=0.6' -F 'camera_id=1' -F 'timestamp=2023-01-01T12:00:00' http://localhost:8001/predict/

Python

import requests

url = "http://localhost:8001/predict/"
files = {"image": open("usdot.jpg", "rb")}
data = {
    "min_detection_score": 0.2,
    "min_ocr_score": 0.6,
    "camera_id": 1,
    "timestamp": "2023-01-01T12:00:00"
}

response = requests.post(url, files=files, data=data)
print(response.json())

JavaScript

const fs = require("fs");
const fetch = require("node-fetch");
const FormData = require("form-data");

const form = new FormData();
form.append("image", fs.createReadStream("usdot.jpg"));
form.append("min_detection_score", "0.2");
form.append("min_ocr_score", "0.6");
form.append("camera_id", "1");
form.append("timestamp", "2023-01-01T12:00:00");

fetch("http://localhost:8001/predict/", { method: "POST", body: form })
  .then((res) => res.json())
  .then((json) => console.log(json));