Plate Recognizer Snapshot

ALPR that Works

ANPR ALPR License plate recognition cars

Snapshot identifies vehicles with or without a license plate present! See our full assessment of ALPR results.

ALPR for Vehicles without license plates

Input Parameters

Image: Send an image in a variety of formats.
Region: Specify the region(s) of interest (e.g. US-CA).
Camera: Specify the camera associated with the image.
Timestamp: Optional.

Output Parameters

Decoded Plate: See license plate(s) decoded.
Region of Plate: Get the region code of decoded vehicle (e.g. AU-VIC).
Vehicle Type: Know if vehicle is a big truck, bus, motorcycle, pickup truck, sedan, SUV, van, or unknown.
Vehicle Make/Model: See make & model from over 9,000 different models.
Vehicle Color: Get color of vehicle.
Orientation: Know front or rear of vehicle.
Additional Candidates: See additional decoded plate possibilities with score.
Bounding Box: Get x, y coordinates of box around each plate.

API Cloud

Requires Internet connection.
Supports images up to 3 MB.
Limit of 8 images per second.
Runs on Linode Cloud servers in New Jersey, USA.

On-Premise SDK

No Internet required, except during set-up.
No image file size limitation.
No limit on # lookups per second.
Runs fast on Windows, Linux, Mac, Jetson, Pi, Zynq, 96Boards, Kubernetes, and more.
Operates on a Docker container with REST API.

Snapshot ALPR Architecture

ALPR Automatic License Plate System Architecture

Process images from VMS, camera, your app or FTP.
Send results via JSON or Webhooks to your system.
Forward ALPR results to ParkPow to get alerts, dashboard, etc.
Send ALPR results to open/close gate (synchronized with ParkPow).

Click image to enlarge.

Simple REST API for ALPR

Request

# Get an image
curl -o /tmp/car.jpg https://platerecognizer.com/static/demo.jpg
# Call the API
curl -F 'upload=@/tmp/car.jpg'   -H 'Authorization: Token 123456'   https://platerecognizer.com/v1/plate-reader

# Get an image

curl -o /tmp/car.jpg https://platerecognizer.com/static/demo.jpg

# Call the API

curl -F 'upload=@/tmp/car.jpg' -H 'Authorization: Token 123456' https://platerecognizer.com/v1/plate-reader

Response

{"filename": "car.jpg",
 "results": [{
     "box": {
         "xmin": 12, "ymin": 84, "ymax": 168, "xmax": 380},
     "plate": "123456",
     "score": 0.90 }]
}

{"filename": "car.jpg",

"results": [{

"box": {

"xmin": 12, "ymin": 84, "ymax": 168, "xmax": 380},

"plate": "123456",

"score": 0.90 }]

}

Integrate with our ALPR API with a few lines of code on a variety of programming languages: Python, Javascript, Ruby, C#, etc.

Get an easy to use JSON response with the number plate value of the vehicle.

See examples of how to interface with our API on this ALPR Github project. You can call the API on all the files of a directory and analyze the frames of a video.

Get Started

Ways to Deploy Plate Recognizer Snapshot

Camera FTP

Upon vehicle detection, camera sends an image via FTP to Snapshot. Or, get ALPR with Axis and Meraki cameras.

API Integration

Send images to our API Cloud or SDK.
Incorporate ALPR output into your app.
See Sample Plate Rec Code in 8 languages.

Video Mgmt Software

We’re pre-integrated with Blue Iris, Network Optix, Milestone and more! The integrations are cloud-based and/or on-premise.

Happy Customers

Get Fast ALPR Quickly

Get ALPR up and running in under 60 minutes. Free Trial with no Credit Card required!

Get Started

Basic Online Dashboard

Get full list of all vehicles decoded.
Search for a specific license plate
Filter results based on camera, start time, end time, or confidence level.
Data stored for 7 days.

Online Dashboard available only for API Cloud customers.

ALPR Dashboard

Proactively get alerts when unauthorized vehicle arrives.
Enforce parking policies (e.g. visitors park for 3 hours max).
Get deep analytics of vehicles entering and exiting.
Search plates by time, site, vehicle type, color, make, etc.
See full details with Vehicle Tags and Vehicle CRM.
Easily import data from other systems.

Learn More

ALPR Dashboard Overview Chart for license plate recognition

Webhooks

Easily create webhooks for API Cloud or SDK to “auto-forward” ALPR output.
Construct one or multiple webhooks per API Cloud account or SDK license.

Learn More

Detection Zone

Mask out areas of the image for engine to ignore.
Specify Detection Zone for each camera.

License Management

Easily see all products purchased.
Describe each SDK license to keep track of them.
See lookup usage for each license.
Move license to another machine.
Activate or disable a license key.

Supported Devices for Snapshot SDK

Windows
Linux
Mac
Raspberry Pi 3 & 4 (32 bit, 64 bit)
Nvidia Jetson Nano, TX1, TX2, Xavier NX
Rock Pi, Orange Pi
LattePanda
Xilinx Zynq
96Boards

SDK Software is executed on a Docker Container.

See HW Requirements

Languages Supported

See Sample Code

Affordable Pricing

Plate Recognizer Snapshot is priced as a subscription fee based on # Lookups per month.

Take advantage of our Free Trial and start today!

See Pricing

Inference Speeds for Snapshot SDK

Inference Speed (ms)	Fast Mode	Regular Mode
n2-standard-8 (8 vCPUs, 32 GB RAM)	21	41
n1-standard-4 (4 vCPUs, 15 GB RAM), 1 x NVIDIA Tesla T4	24	44
c2-standard-4 (4 vCPUs, 16 GB RAM)	30	58
n2-standard-4 (4 vCPUs, 16 GB RAM)	33	64
Intel Core i7-8550U CPU @ 1.80GHz	33	55
n1-standard-4 (4 vCPUs, 15 GB RAM)	47	94
n2-standard-2 (2 vCPUs, 8 GB RAM)	58	108
e2-standard-2 (2 vCPUs, 8 GB RAM)	77	145
LattePanda Alpha	119	170
Nvidia Jetson Nano	250	300
LattePanda V1	875	1250
Raspberry Pi 3/4	1000	1300

* Speeds based on HD Image size (1280 x 720). Fast Mode can be used in situations where vehicle size is at least 10% of image size. Otherwise, Regular Mode is recommended. For details, go to our GitHub page on ALPR Speeds.

Need Help with ALPR?

Let us know and we’d be happy to assist.