License Plate Recognition
Detects vehicle license plates in real time from the camera video and reads their text. The plate model is chosen in the analyzer setting Region: Latin (EU/US/SouthAmerica) (default) or Korea.
- Results from several frames are corrected by majority voting, which automatically fixes single-frame misreads.
- A minimum confidence filter removes noisy results.
Commands
| Command | Description |
|---|
| Scan | Writes the text, region, and confidence of the top-confidence plate. |
| Scan All | Writes every detected plate as a JSON array. |
| Has Plate? | Checks whether a plate is detected. |
| Count Plates | Writes the number of detected plates. |
Settings
| Setting | Description |
|---|
| Min Confidence (%) | Only plates with confidence at or above this value are included. 0 to 100, default 50. |
Output Variables
| Field | Type | Value |
|---|
| Detected | Digital | True when a plate is detected. |
| Plate Text | Text | The recognized plate string. |
| Detected Region | Text | The country of the plate as classified by the model (e.g. Argentina, Germany, Korea). |
| Confidence (%) | Number | Average text recognition confidence, 0 to 100. |
| Count | Number | Number of detected plates. |
| Output (JSON Text) | Text | Array of every detected plate. |
JSON Output
An array with, per plate, text, region, confidence (text recognition confidence, 0 to 100), the plate detection stage score det_score, the center x and y, width, and height.
[
{ "text": "ABC1234", "region": "Argentina", "confidence": 92, "det_score": 0.97, "x": 320, "y": 240, "width": 120, "height": 40 }
]