administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-04-15 19:42:08 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update docs/docs/configuration/license_plate_recognition.md

Browse Source 
Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
This commit is contained in:
AmirHossein_Omidi 2025-10-01 16:43:15 +03:30 committed by GitHub
parent 1f7b45029a
commit 004d9f5ec1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/docs/configuration/license_plate_recognition.md
View File

@ -28,14 +28,6 @@ In the default mode, Frigate's LPR needs to first detect a `car` or `motorcycle`
:::
## OCR Model Details
Frigate uses **PaddleOCR** (via an ONNX runtime) to perform text recognition on detected license plates. This model extracts characters from license plates and populates the `recognized_license_plate` field or a `sub_label` for tracked `car` or `motorcycle` objects. PaddleOCR provides accurate recognition even in challenging lighting and motion conditions, and it is lightweight enough to run on CPU or GPU depending on your configuration.
- The PaddleOCR ONNX model is used internally and can be replaced with custom OCR models if desired.
- For more details, visit the [PaddleOCR GitHub repository](https://github.com/PaddlePaddle/PaddleOCR).
## Minimum System Requirements
License plate recognition works by running AI models locally on your system. The YOLOv9 plate detector model and the OCR models ([PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)) are relatively lightweight and can run on your CPU or GPU, depending on your configuration. At least 4GB of RAM is required.