Sign Up

ANPR Detection Zone

This article describes how to apply Detection Zones for your automatic number  plate recognition (ANPR) project.

Let’s face it–in life, there are things that get in the way of a perfect picture.  This can certainly apply for license plate recognition cameras–where we want to focus on one part of the camera view but not the other.

We start first with the original image–with a silver SUV on the left and a white minivan on the right.

ALPR detection zone original image

Original image used to demonstrate Detection Zone  Source: Plate Recognizer.

How to Use Detection Zone

You can use Detection Zone on Snapshot Cloud, Snapshot SDK and also Stream.  

Step 1: Make sure that Plate Recognizer software has Internet access and go to Detection Zone. 

Step 2: Make sure to put in the correct, full Camera ID for the camera that you want to apply Detection Zone.

Step 3: Upload a sample image from that camera.  Click Add Zone.

Step 4: Select the approrpriate marker thickness and then use the masking marker to shade out the areas you want to ignore.  Click to Save Zone.

Step 5: Restart Stream or Snapshot SDK (requires Internet connectivity) and the newly created Detection Zone will automatically apply.  No action needed for Snapshot Cloud.

Detection Zone UI in Plate Recognizer. Source: Plate Recognizer.

1) Mask Part of the Vehicle, But Not the Plate

TEST: We cover the top part of the left SUV and the right part of the minivan.  The license plate portion is not covered.

RESULT: Both license plates are fully (and correctly) identified. 

ANPR mask part of vehicle
ANPR mask over part of vehicle results

License plate not masked so we identify the full plates.  Source: Plate Recognizer.

2) Cover Portion of License Plate, But Not Plate Characters

TEST: We block out the edges of the license plate but are careful not to touch the characters themselves.

RESULT: Both license plates are fully (and correctly) identified.

Small part of license is covered.  We still  identify the full plates.  Source: Plate Recognizer.

3) Cover Portion of License Plate Characters

TEST: We block out the last 3 characters of the white minivan.

RESULT: Only the first 3 characters of the minivan license plate is identified. 

Cover part of license plate results

Left part of minivan plate is covered.  We decode the portion of plate uncovered. Source: Plate Recognizer.

4) Cover Most of Vehicle, Including All of License Plate

TEST: We block out 70% of the white minivan.

RESULT: License plate of minivan is not detected. 

ALPR detection zone over most of vehicle
ALPR Detection Zone over most of vehicle results

Most of white minivan is covered.  Engine is not able to detect minivan license plate. Source: Plate Recognizer.

Tips on Using Detection Zone

Regardless of which Plate Recognizer product you intend to use, we recommend applying Detection Zone via Snapshot Cloud and then uploading some images to our Snapshot Cloud to test.  

This way, you can review the ALPR results before deploying.

Need help?  Let us know.  

Contact Us

Have a question about ALPR or Parking Management Software? Contact Us

About Plate Recognizer

Plate Recognizer provides accurate, fast, developer-friendly Automatic License Plate Recognition (ALPR) software that works in all environments, optimized for your location. Sign up for a Free Trial!

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from Youtube
Consent to display content from Vimeo
Google Maps
Consent to display content from Google
Consent to display content from Spotify
Sound Cloud
Consent to display content from Sound