← Back to Articles

Platerecognizer utility for ANPR module in Xeoma

Sometimes it’s not that easy to decode a license plate if the image is blurry or somehow distorted. Xeoma provides multiple ways to enhance license plates recognition by using different utilities such as OpenALPR, iANPR and now – Platerecognizer. It’s an accurate and fast license plates recognition utility that can work with different license plates. Platerecognizer’s algorithms are able to handle plates that are blurry, dark, angled, with stacked characters, etc. It supports over 90 countries.

Platerecognizer utility can work both as a cloud software and as a local software (no Internet required) on a variety of hardware.

Let’s review step-by-step instruction on how to use Platerecognizer utility (and test it).

1. Please visit platerecognizer.com and sign up to receive API key for testing and using the utility free of charge (or purchase necessary product for your requirements):

2. After you confirm your email address, you’ll receive API token:

3. Next you’ll need to open Xeoma (you can download Trial version of Xeoma here) and add ANPR module in your modules chain:

4. Then you’ll need to tick Platerecognizer.com option in ANPR module’s settings and specify HTTP address of the recognition service: https://api.platerecognizer.com/v1/plate-reader (this is the address for Cloud API, if you need to use local (on-premise) software, then please do not change this HTTP address of the recognition service field)

5. If everything is configured correctly, you’ll see license plate recognition in Xeoma:

6. Snapshots/video with decoded license plates can be checked both in your account on platerecognizer.com and in Xeoma:

As you can see, configuration of this utility is really easy. Platerecognizer utility’s algorithms will be a great tool to improve license plate recognition accuracy thanks to its adjustment to various “real-life” factors, such as sun glare, blurry images, fast vehicles, night-time, and many more.

And here is the instruction for local/on-premise SDK installation (on your own computer) click here…

1. First, you need to configure “Platerecognizer” utility according to this instruction

2. Then you need to specify URL for local SDK in Xeoma: http://localhost:8080/alpr

3. ‘localhost’ can be replaced with ip address of the device where Platerecognizer SDK is configured

 

Watch video about License Plate Recognizer

License Plates Recognizer in pictures:

 

Please feel free to contact us if you need help with configuration or any other assistance, we’re always happy to help!

How do I send less pictures to Platerecognizer? (click to read)

If the goal of the setup is to send to Platerecognizer only the license plates that move in a selected area in the selected direction, right?
In this case the scheme that you have now might be improved in the following ways:

1. If you have the Cross-Line Detector module is after the ANPR – this is great if you need to save only episodes of where LPs are moving in the right direction. BUT all LPs are sent to Platerecognizer in this setup, and filtering by direction happens after we get the response.
If it’s critical to filter our direction before sending LPs to Platerecognizer then we’d need to redo the scheme placing the Cross-Line Detector before ANPR. However, the Cross-Line doesn’t work without a module that tells it about the object type (in the scheme where Cross-Line is placed after the ANPR this role is played by the ANPR) so we’d need an Object Recognizer module where you need to tick object type (car). OR instead of the ‘Object Recognizer’ module you could use ‘Object Detector’ module – it reacts to any objects, no matter their type – but we don’t really need it in here.
In Cross-Line place the line with the direction going in which you want to “catch” cars.

2. If image crop is needed, you can use the Image Crop module, it is better placed after the camera in the chain.

3. Important ANPR should have these settings:
Recognize only changed areas: ticked
Detection Interval: higher than the default 50 ms (=0.05 of a second, default timeout). Try different values to find the best – to not miss anything (lower than 2000ms) and yet to not send too many pics to PR (higher than 50ms).

Please feel free to contact us if you need assistance regarding Xeoma!

August, 27 2019

Read also:
ANPR module in Xeoma
Instruction for ANPR module in Xeoma
Additional modules in Xeoma
Object recognizer in Xeoma
Rent of the license is the best way to launch a new project
GPIO module in Xeoma
Object recognition in private life