Fix facial recognition

Scaling still seems to be imperfect

.vscode/launch.json

@@ -8,7 +8,7 @@
             "name": "Python: Module",
             "type": "python",
             "request": "launch",
-            "module": "set-detect-notify",
+            "module": "set_detect_notify",
             "justMyCode": true
         }
     ]

set_detect_notify/__main__.py

@@ -46,7 +46,8 @@ def main():
         # Set it to the env RUN_SCALE if it isn't blank, otherwise set it to 0.25
         default=os.environ["RUN_SCALE"]
         if "RUN_SCALE" in os.environ and os.environ["RUN_SCALE"] != ""
-        else 0.25,  # noqa: E501
+        # else 0.25,  
+        else 1,  
         type=float,
         help="The scale to run the detection at, default is 0.25",
     )
@@ -55,7 +56,8 @@ def main():
         # Set it to the env VIEW_SCALE if it isn't blank, otherwise set it to 0.75
         default=os.environ["VIEW_SCALE"]
         if "VIEW_SCALE" in os.environ and os.environ["VIEW_SCALE"] != ""
-        else 0.75,  # noqa: E501
+        # else 0.75,  
+        else 1,  
         type=float,
         help="The scale to view the detection at, default is 0.75",
     )
@@ -191,6 +193,26 @@ def main():
         for i, r in enumerate(results):
             # list of dicts with each dict containing a label, x1, y1, x2, y2
             plot_boxes = []
+
+            # The following is stuff for people
+            # This is still in the for loop as each result, no matter if anything is detected, will be present.
+            # Thus, there will always be one result (r)
+            if face_details := utils.recognize_face(path_to_directory=Path(args.faces_directory), run_frame=run_frame):
+                plot_boxes.append( face_details  )
+                objects_and_peoples=notify.thing_detected(
+                    thing_name=face_details["label"],
+                    objects_and_peoples=objects_and_peoples,
+                    detection_type="peoples",
+                    detection_window=args.detection_window,
+                    detection_duration=args.detection_duration,
+                    notification_window=args.notification_window,
+                    ntfy_url=args.ntfy_url,
+                )
+
+
+
+
+            # The following is stuff for objects
             # Setup dictionary of object names
             if objects_and_peoples["objects"] == {} or objects_and_peoples["objects"] is None:
                 for name in r.names.values():

set_detect_notify/utils/notify.py

@@ -44,6 +44,7 @@ def thing_detected(
     respective_type = objects_and_peoples[detection_type]
 
     # (re)start cycle
+    try:
         if (
             # If the object has not been detected before
             respective_type[thing_name]["last_detection_time"] is None
@@ -63,7 +64,7 @@ def thing_detected(
                 )
             respective_type[thing_name]["detection_duration"] = 0
         else:
-        # Check if the last notification was less than 15 seconds ago
+            # Check if the last NOTIFICATION was less than 15 seconds ago
             # If it was, then don't do anything
             if (
                 time.time() - respective_type[thing_name]["last_detection_time"]
@@ -80,6 +81,14 @@ def thing_detected(
             )
             # print("Updating detection duration")
             respective_type[thing_name]["last_detection_time"] = time.time()
+    except KeyError:
+        # If the object has not been detected before
+        respective_type[thing_name] = {
+            "last_detection_time": time.time(),
+            "detection_duration": 0,
+            "last_notification_time": None,
+        }
+        print(f"First detection of {thing_name} ever")
 
     # (re)send notification
     # Check if detection has been ongoing for 2 seconds or more in the past 15 seconds

set_detect_notify/utils/utils.py

@@ -3,6 +3,8 @@ import numpy as np
 from pathlib import Path
 from deepface import DeepFace
 
+first_face_try = True
+
 def plot_label(
     # list of dicts with each dict containing a label, x1, y1, x2, y2
     boxes: list = None,
@@ -67,7 +69,7 @@ def recognize_face(
     Accepts a path to a directory of images of faces to be used as a refference
     In addition, accepts an opencv image to be used as the frame to be searched
     
-    Returns a list of dictionaries, containing a single dictonary as currently only 1 face can be detected in each frame
+    Returns a single dictonary as currently only 1 face can be detected in each frame
     dict contains the following keys: label, x1, y1, x2, y2
     The directory should be structured as follows:
     faces/
@@ -84,8 +86,23 @@ def recognize_face(
     Point is, `name` is the name of the person in the images in the directory `name`
     That name will be used as the label for the face in the frame
     '''
+    global first_face_try
+
+    # If it's the first time the function is being run, remove representations_vgg_face.pkl, if it exists
+    if first_face_try:
+        try:
+            Path("representations_vgg_face.pkl").unlink()
+            print("Removing representations_vgg_face.pkl")
+        except FileNotFoundError:
+            pass
+        first_face_try = False
+
     # face_dataframes is a vanilla list of dataframes
-    face_dataframes = DeepFace.find(run_frame, db_path=str(path_to_directory))
+    try:
+        face_dataframes = DeepFace.find(run_frame, db_path=str(path_to_directory), enforce_detection=True, silent=True)
+    except ValueError as e:
+        if str(e) == "Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.":
+            return None
     # Iteate over the dataframes
     for df in face_dataframes:
         # The last row is the highest confidence
@@ -103,8 +120,12 @@ def recognize_face(
             "x2": df.iloc[-1]["source_x"] + df.iloc[-1]["source_w"],
             "y2": df.iloc[-1]["source_y"] + df.iloc[-1]["source_h"],
         }
-        
+        distance = df.iloc[-1]["VGG-Face_cosine"]
-        return [dict(label=label, **coordinates)]
+        # if 0.5 < distance < 0.7:
+            # label = "Unknown"
+        to_return = dict(label=label, **coordinates)
+        print(f'Confindence: {distance}, filname: {path_to_image.name}, to_return: {to_return}')
+        return to_return
 
     '''
     Example dataframe, for reference