Our service offers great reading accuracy but it won’t work in certain cases. As a rule of thumb if a human has a hard time reading the license plate, our service then may not be able to read it. If a human is able to read the license plate, we will most likely be able to read it too. The main use case for our service is automation.
Yes. Our On-Premise SDK can run on your server or device. The SDK does not need an Internet connection. The SDK is a Docker container with a REST API.
You will need a Linux machine with at least 2g of RAM. It can also run on a Raspberry Pi device. Inference speed on a recent mid range CPU is 100ms.
You can find the documentation and examples of code on our API documentation page.
We have added a number of algorithms in our LPR solution to take into account various real-life situations, such as blurry images, diverse lighting conditions, low resolution, images with vehicles taken from the side, etc.
Here’s an example:
curl -o c:car.jpg https://platerecognizer.com/static/demo.jpg
curl -F "upload=@c:car.jpg" -H "Authorization: Token my-unique-token" https://api.platerecognizer.com/v1/plate-reader