Automatic License Plate Recognition Software (ALPR, ANPR)

Get high-accuracy, developer-friendly automatic license plate recognition (ALPR) or automatic number plate recognition (ANPR) software! The core of our ALPR, ANPR system is based on state of the art deep neural networks architectures.

Reading License Plates from Images
Number Plate Recognition on a Video or Camera Stream
Automatic Image Transfer
Code Samples

Our machine-learning software:

Works on dark, low-res, blurry images and tough angles, all vehicle types, etc. See our full ALPR results.
Decodes license plate , vehicle type (e.g. SUV, van, pickup truck), vehicle make model (e.g. Honda Accord), color, and orientation. Ignores bumper stickers, car signs, etc.
Is optimized for all 50 USA States, India, Brazil and 90+ countries worldwide.

Snapshot : Get license plate reader from images in under 60 minutes:

Access a simple REST API for easy integration in 8 programming languages.
Returns results via JSON Response or Webhooks.
Has fast inference speed up to 21 ms.
Runs on-premise on Linux, Windows , Mac, Jetson , Kubernetes, Raspberry Pi, Zynq, 96Boards, LattePanda and more.

Stream : Get number plate recognition from camera or video feed:

Returns license plate results via CSV file or Webhooks.
Handles 4 cameras simultaneously on mid-range PC.
Runs on-premise on Linux, Windows , Mac and Jetson.

ALPR, ANPR software is ideal for parking, highway monitoring, toll, police surveillance, community security, and other use cases. Our license plate recognition (LPR) software can also forward results to our full ALPR Dashboard and Parking Management software solution, ParkPow. Sign up for a Free Trial now (no credit card required) or learn more at https://platerecognizer.com.

Reading License Plates from Images

Get your API key from Plate Recognizer. Replace MY_API_KEY with your API key and run the command below.

# Getting started!
git clone https://github.com/marcbelmont/deep-license-plate-recognition.git
cd deep-license-plate-recognition
pip install requests pillow

python plate_recognition.py --api-key MY_API_KEY /path/to/vehicle.jpg

The result includes the bounding boxes (rectangle around object) and the plate value for each plate. View the details of the results on our documentation.

[
  {
    "version": 1,
    "results": [
      {
        "box": {
          "xmin": 85,
          "ymin": 85,
          "ymax": 211,
          "xmax": 331
        },
        "plate": "ABC123",
        "score": 0.904,
        "dscore": 0.92
      }
    ],
    "filename": "car.jpg"
  }
]

Lookups For a Specific Region

You can match the license plate patterns of a specific region.

python plate_recognition.py --api-key MY_API_KEY --regions fr --regions it /path/to/car.jpg

Process Multiple Files (Batch Mode)

You can also run the license plate reader on many files at once. To run the script on all the images of a directory, use:

python plate_recognition.py --api-key MY_API_KEY /path/to/car1.jpg /path/to/car2.jpg /path/to/trucks*.jpg

Running the ALPR Locally (SDK)

To use a locally hosted sdk, pass the url to the docker container as follows:

python plate_recognition.py --sdk-url http://localhost:8080 /path/to/vehicle.jpg

Blurring License Plates and Redaction

The script number_plate_redaction.py differs from the default prediction script because it also detects plates that are barely readable and/or very small. It returns the bounding boxes of all the license plates. They can be used to blur or mask the license plates.

In addition, it can split the image in smaller images to better deal with high resolution images. This will use 3 lookups instead of just 1. To use this options add --split-image.

The option --save-blurred lets you save blurred images. They are saved to a new file with _blurred suffix.

The option --ignore-regexp lets you specify a regex of plates to ignore from blur. This option can be specified multiple times.

The option --ignore-no-bb lets you ignore recognitions without a vehicle bounding box from blur.

python number_plate_redaction.py --help
python number_plate_redaction.py --api-key API_KEY vehicels.jpg
python number_plate_redaction.py --sdk-url http://localhost:8080 --split-image vehicels.jpg

python number_plate_redaction.py --api-key 77c### 58C5A57_14965463.jpg --save-blurred --ignore-regexp ^58c5a57$ --ignore-regexp ^[0-9][0-9]c5a57$

Process images from an FTP server

To process images from the FTP server run ftp_processor script:

python ftp_processor.py --api-key MY_API_KEY --ftp-host hostname --ftp-user user --ftp-password password --folder /path/to/server_folder

To remove images from FTP server after processing, add the argument --delete.

Automatic Image Transfer

Automatic Image Transfer is a command line tool that runs our ALPR Engine. It monitors a folder and automatically process images (Cloud or SDK) as they are added. Once processed, images are moved to an archive directory. It can also forward the results to our parking management service Parkpow.

To get started: python transfer.py --help

Code Samples

See our sample projects to easily get started with the API.

Example program in C++.
Example program in C#.
Example program in Java.
Android App. It lets you take a picture and send it to our API.
View how to integrate with other languages in our documentation.
A Node-RED node for license plate recognition.

Have questions? Let us know how we can help.

Provided by Plate Recognizer, a subsidiary of ParkPow.

vivahome/deep-license-plate-recognition