Update app.py

app.py

@@ -18,43 +18,63 @@ def detect_emotion(face_landmarks):
     A simple mock-up function for detecting emotions based on landmarks.
     Replace with a more sophisticated model as needed.
     """
-    # Example: Arbitrarily assign "Happy" if eyes are close together
     if face_landmarks:
+        # Example: Assign "Happy" if eyes are close together
         return "Happy"
     return "Neutral"
 
+# Resize image to reduce memory usage
+def resize_image(image, max_size=(800, 800)):
+    """
+    Resizes the image to the specified maximum size while maintaining aspect ratio.
+    """
+    image.thumbnail(max_size, Image.ANTIALIAS)
+    return image
+
 # Process the uploaded image
 if uploaded_file is not None:
-    image = Image.open(uploaded_file)
-    image_np = np.array(image)
-
-    # Convert image to RGB
-    rgb_image = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
-
-    # Detect faces in the image
-    face_locations = face_recognition.face_locations(rgb_image)
-    face_landmarks_list = face_recognition.face_landmarks(rgb_image)
-
-    if face_locations:
-        for face_location, face_landmarks in zip(face_locations, face_landmarks_list):
-            # Draw a rectangle around the face
-            top, right, bottom, left = face_location
-            cv2.rectangle(image_np, (left, top), (right, bottom), (0, 255, 0), 2)
-
-            # Detect emotion based on landmarks
-            emotion = detect_emotion(face_landmarks)
-
-            # Display emotion above the face
-            cv2.putText(
-                image_np,
-                emotion,
-                (left, top - 10),
-                cv2.FONT_HERSHEY_SIMPLEX,
-                0.9,
-                (255, 0, 0),
-                2,
-            )
-
-        st.image(image_np, caption="Processed Image", use_column_width=True)
+    # Check file size to prevent loading large images
+    if uploaded_file.size > 10 * 1024 * 1024:  # 10 MB limit
+        st.error("File too large. Please upload an image smaller than 10 MB.")
     else:
-        st.warning("No faces detected in the image.")
+        # Open and resize the image
+        image = Image.open(uploaded_file)
+        image = resize_image(image)
+
+        # Convert image to numpy array
+        image_np = np.array(image)
+
+        # Convert image to RGB (ensure compatibility with face_recognition)
+        if len(image_np.shape) == 3 and image_np.shape[2] == 4:  # RGBA to RGB
+            image_np = cv2.cvtColor(image_np, cv2.COLOR_RGBA2RGB)
+        elif len(image_np.shape) == 3 and image_np.shape[2] == 3:  # BGR to RGB
+            image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)
+
+        # Detect faces and landmarks
+        face_locations = face_recognition.face_locations(image_np)
+        face_landmarks_list = face_recognition.face_landmarks(image_np)
+
+        if face_locations:
+            for face_location, face_landmarks in zip(face_locations, face_landmarks_list):
+                # Draw a rectangle around the face
+                top, right, bottom, left = face_location
+                cv2.rectangle(image_np, (left, top), (right, bottom), (0, 255, 0), 2)
+
+                # Detect emotion based on landmarks
+                emotion = detect_emotion(face_landmarks)
+
+                # Display emotion above the face
+                cv2.putText(
+                    image_np,
+                    emotion,
+                    (left, top - 10),
+                    cv2.FONT_HERSHEY_SIMPLEX,
+                    0.9,
+                    (255, 0, 0),
+                    2,
+                )
+
+            # Display the processed image
+            st.image(image_np, caption="Processed Image", use_column_width=True)
+        else:
+            st.warning("No faces detected in the image.")