Detect
A YOLOv5 detector locates the licence plate in the frame and returns its bounding box.
Demo 01 Computer vision for vehicles
Read a licence plate from a photo.
Drop in a vehicle image. The detector locates the plate, crops it and returns the characters in a single request. The live demo runs on our public endpoint, so you can test it with your own photos before you integrate.
- No key needed on the demo endpoint
- Ten requests a minute per visitor
- One response with the reading and the plate crop
One request, three stages
From image to readable plate.
The same pipeline powers the demo and the production API. Each stage is a model we train and tune for your cameras.
Crop and normalise
The plate region is cropped and prepared for recognition, reducing the effect of framing, angle and lighting.
Read
A CRNN recogniser returns the characters as plain text, alongside the crop so you can verify the reading.
Built for production systems
One POST. One JSON response.
Call the hosted API from any HTTP client. Tenant keys keep requests attributable, and errors are predictable, so integrations are straightforward to operate.
422No licence plate detected413Image exceeds the upload limit415File is not an image
Request
curl -X POST https://<your-host>/api/detect/ \
-H "X-API-Key: $LP_OCR_API_KEY" \
-F "file=@vehicle.jpg"Response
{
"recognition_result": "rk959ad",
"cropped_image_base64": "/9j/4AAQSkZJRgABAQ..."
}Tune it to the real world
Designed around your cameras, plates and operating conditions.
Access control
Automate vehicle entry at car parks, estates, campuses and secured facilities.
Fleet operations
Turn images from yards, depots and weighbridges into searchable vehicle events.
Regional formats
Fine-tune recognition for local character sets, layouts, fonts and mixed fleets.
Start with a real image
See what your camera can read.
Try the demo with your own photos, then talk to us about tuning the model for your site.
Browse all demos