Use regular expressions for plate matching (#14727)

docs/docs/configuration/license_plate_recognition.md

@@ -26,7 +26,7 @@ lpr:
 
 Several options are available to fine-tune the LPR feature. For example, you can adjust the `min_area` setting, which defines the minimum size in pixels a license plate must be before LPR runs. The default is 500 pixels.
 
-Additionally, you can define `known_plates`, allowing Frigate to label tracked vehicles with custom sub_labels when a recognized plate is detected. This information is then accessible in the UI, filters, and notifications.
+Additionally, you can define `known_plates` as strings or regular expressions, allowing Frigate to label tracked vehicles with custom sub_labels when a recognized plate is detected. This information is then accessible in the UI, filters, and notifications.
 
 ```yaml
 lpr:
@@ -37,12 +37,9 @@ lpr:
       - "ABC-1234"
       - "ABC-I234"
     Johnny:
-      - "JHN-1234"
+      - "J*N-*234" # Using wildcards for H/M and 1/I
-      - "JMN-1234"
-      - "JHN-I234"
     Sally:
-      - "SLL-1234"
+      - "[S5]LL-1234" # Matches SLL-1234 and 5LL-1234
-      - "5LL-1234"
 ```
 
 In this example, "Wife's Car" will appear as the label for any vehicle matching the plate "ABC-1234." The model might occasionally interpret the digit 1 as a capital I (e.g., "ABC-I234"), so both variations are listed. Similarly, multiple possible variations are specified for Johnny and Sally.

frigate/embeddings/embeddings.py

@@ -154,7 +154,7 @@ class Embeddings:
                     "detection.onnx": "https://github.com/hawkeye217/paddleocr-onnx/raw/refs/heads/master/models/detection.onnx"
                 },
                 model_size="large",
-                model_type=ModelTypeEnum.alpr_detect,
+                model_type=ModelTypeEnum.lpr_detect,
                 requestor=self.requestor,
                 device="CPU",
             )
@@ -166,7 +166,7 @@ class Embeddings:
                     "classification.onnx": "https://github.com/hawkeye217/paddleocr-onnx/raw/refs/heads/master/models/classification.onnx"
                 },
                 model_size="large",
-                model_type=ModelTypeEnum.alpr_classify,
+                model_type=ModelTypeEnum.lpr_classify,
                 requestor=self.requestor,
                 device="CPU",
             )
@@ -178,7 +178,7 @@ class Embeddings:
                     "recognition.onnx": "https://github.com/hawkeye217/paddleocr-onnx/raw/refs/heads/master/models/recognition.onnx"
                 },
                 model_size="large",
-                model_type=ModelTypeEnum.alpr_recognize,
+                model_type=ModelTypeEnum.lpr_recognize,
                 requestor=self.requestor,
                 device="CPU",
             )

frigate/embeddings/functions/onnx.py

@@ -38,9 +38,9 @@ class ModelTypeEnum(str, Enum):
     face = "face"
     vision = "vision"
     text = "text"
-    alpr_detect = "alpr_detect"
+    lpr_detect = "lpr_detect"
-    alpr_classify = "alpr_classify"
+    lpr_classify = "lpr_classify"
-    alpr_recognize = "alpr_recognize"
+    lpr_recognize = "lpr_recognize"
 
 
 class GenericONNXEmbedding:
@@ -142,11 +142,11 @@ class GenericONNXEmbedding:
                 self.feature_extractor = self._load_feature_extractor()
             elif self.model_type == ModelTypeEnum.face:
                 self.feature_extractor = []
-            elif self.model_type == ModelTypeEnum.alpr_detect:
+            elif self.model_type == ModelTypeEnum.lpr_detect:
                 self.feature_extractor = []
-            elif self.model_type == ModelTypeEnum.alpr_classify:
+            elif self.model_type == ModelTypeEnum.lpr_classify:
                 self.feature_extractor = []
-            elif self.model_type == ModelTypeEnum.alpr_recognize:
+            elif self.model_type == ModelTypeEnum.lpr_recognize:
                 self.feature_extractor = []
 
             self.runner = ONNXModelRunner(
@@ -223,17 +223,17 @@ class GenericONNXEmbedding:
 
             frame = np.expand_dims(frame, axis=0)
             return [{"input_2": frame}]
-        elif self.model_type == ModelTypeEnum.alpr_detect:
+        elif self.model_type == ModelTypeEnum.lpr_detect:
             preprocessed = []
             for x in raw_inputs:
                 preprocessed.append(x)
             return [{"x": preprocessed[0]}]
-        elif self.model_type == ModelTypeEnum.alpr_classify:
+        elif self.model_type == ModelTypeEnum.lpr_classify:
             processed = []
             for img in raw_inputs:
                 processed.append({"x": img})
             return processed
-        elif self.model_type == ModelTypeEnum.alpr_recognize:
+        elif self.model_type == ModelTypeEnum.lpr_recognize:
             processed = []
             for img in raw_inputs:
                 processed.append({"x": img})

frigate/embeddings/maintainer.py

@@ -3,6 +3,7 @@
 import base64
 import logging
 import os
+import re
 import threading
 from multiprocessing.synchronize import Event as MpEvent
 from pathlib import Path
@@ -23,7 +24,7 @@ from frigate.comms.events_updater import EventEndSubscriber, EventUpdateSubscrib
 from frigate.comms.inter_process import InterProcessRequestor
 from frigate.config import FrigateConfig
 from frigate.const import CLIPS_DIR, FRIGATE_LOCALHOST, UPDATE_EVENT_DESCRIPTION
-from frigate.embeddings.alpr.alpr import LicensePlateRecognition
+from frigate.embeddings.lpr.lpr import LicensePlateRecognition
 from frigate.events.types import EventTypeEnum
 from frigate.genai import get_genai_client
 from frigate.models import Event
@@ -683,13 +684,16 @@ class EmbeddingMaintainer(threading.Thread):
             )
             return
 
-        # Determine subLabel based on known plates
+        # Determine subLabel based on known plates, use regex matching
         # Default to the detected plate, use label name if there's a match
-        sub_label = top_plate
+        sub_label = next(
-        for label, plates in self.lpr_config.known_plates.items():
+            (
-            if top_plate in plates:
+                label
-                sub_label = label
+                for label, plates in self.lpr_config.known_plates.items()
-                break
+                if any(re.match(f"^{plate}$", top_plate) for plate in plates)
+            ),
+            top_plate,
+        )
 
         # Send the result to the API
         resp = requests.post(