make the face detection 3D and add comments

app.py

@@ -32,9 +32,12 @@ def count_files_in_directory(directory):
     return file_count
 
 # Determine face shape
-def determine_face_shape(landmarks):
+def determine_face_shape_3d(landmarks):
+    # Calculate 3D distances
     jaw_width = np.linalg.norm(landmarks[0] - landmarks[16])
     face_height = np.linalg.norm(landmarks[8] - landmarks[27])
+
+    # Determine face shape based on 3D proportions
     if jaw_width / face_height > 1.5:
         return "Round"
     elif jaw_width / face_height < 1.2:
@@ -169,10 +172,12 @@ def change_lip_color(frame, color_name='none'):
     return frame
 
 # Process frame for overlay and face shape detection
-def process_frame(frame):
+def process_frame_3d(frame):
     global overlay
+
     frame = np.array(frame, copy=True)
     height, width = frame.shape[:2]
+
     face_detector.setInputSize((width, height))
     _, faces = face_detector.detect(frame)
 
@@ -215,8 +220,9 @@ def process_frame(frame):
                 print(f"Error overlaying glasses: {e}")
 
             for face_landmarks_mp in results.multi_face_landmarks:
-                landmarks = np.array([(lm.x * frame.shape[1], lm.y * frame.shape[0]) for lm in face_landmarks_mp.landmark])
-                face_shape = determine_face_shape(landmarks)
+                # Convert landmarks to 3D coordinates
+                landmarks = np.array([(lm.x * frame.shape[1], lm.y * frame.shape[0], lm.z * frame.shape[1]) for lm in face_landmarks_mp.landmark])
+                face_shape = determine_face_shape_3d(landmarks)
                 glass_shape = recommend_glass_shape(face_shape)
 
     return frame, face_shape, glass_shape
@@ -225,13 +231,13 @@ def process_frame(frame):
 def transform_cv2(frame, transform):
     if transform == "cartoon":
         # prepare color
-        img_color = cv2.pyrDown(cv2.pyrDown(frame))
+        img_color = cv2.pyrDown(cv2.pyrDown(frame)) # Reduce the resolution
         for _ in range(6):
-            img_color = cv2.bilateralFilter(img_color, 9, 9, 7)
-        img_color = cv2.pyrUp(cv2.pyrUp(img_color))
+            img_color = cv2.bilateralFilter(img_color, 9, 9, 7) # Smoothen the image while preserving the edges
+        img_color = cv2.pyrUp(cv2.pyrUp(img_color)) # Scale back to the original resolution
 
         # prepare edges
-        img_edges = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
+        img_edges = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY) # Convert to grayscale
         img_edges = cv2.adaptiveThreshold(
             cv2.medianBlur(img_edges, 7),
             255,
@@ -239,11 +245,12 @@ def transform_cv2(frame, transform):
             cv2.THRESH_BINARY,
             9,
             2,
-        )
-        img_edges = cv2.cvtColor(img_edges, cv2.COLOR_GRAY2RGB)
+        ) # Apply adaptive thresholding to get the edges
+        img_edges = cv2.cvtColor(img_edges, cv2.COLOR_GRAY2RGB) # Convert back to color
         # combine color and edges
         img = cv2.bitwise_and(img_color, img_edges)
-        return img
+        return img # Combine the color and edges
+    
     elif transform == "edges":
         # perform edge detection
         img = cv2.cvtColor(cv2.Canny(frame, 100, 200), cv2.COLOR_GRAY2BGR)
@@ -256,7 +263,6 @@ def transform_cv2(frame, transform):
                            [0.393, 0.769, 0.189]])
         img = cv2.transform(frame, kernel)
         img = np.clip(img, 0, 255)  # ensure values are within byte range
-        # Convert BGR to RGB if necessary (for display purposes)
         img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
         return img_rgb
 
@@ -301,7 +307,7 @@ def save_frame(frame):
        return filename
 
 def webcam_input(frame, transform, lip_color):
-    frame, face_shape, glass_shape = process_frame(frame)
+    frame, face_shape, glass_shape = process_frame_3d(frame)
     if transform != "none" and lip_color == "none":
         frame = transform_cv2(frame, transform)
     elif lip_color != "none" and transform == "none":