Update app.py


app.py

@@ -1,70 +1,54 @@
-# app.py
 import streamlit as st
-try:
-    import cv2
-    st.write("OpenCV successfully imported!")
-except ImportError as e:
-    st.error(f"Error importing OpenCV: {e}")
-
-import streamlit as st
-import cv2
-import numpy as np
-from PIL import Image
-
-# Load Haar Cascade
-@st.cache_resource
-def load_cascade():
-    cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
-    if cascade.empty():
-        raise Exception("Haar Cascade file not loaded!")
-    return cascade
-
-# Detect faces
-def detect_faces(image, face_cascade):
-    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5)
-    for (x, y, w, h) in faces:
-        cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 2)
-    return image, len(faces)
-
-# Streamlit app
-def main():
-    st.title("Real-Time Face Detection App")
-    st.write("Upload an image, and the app will detect faces!")
-
-    # Load Haar Cascade
-    face_cascade = load_cascade()
-    import streamlit as st
 import cv2
 import numpy as np
 from PIL import Image
 import os
 
-# Load Haar Cascade
-@st.cache_resource
+# Ensure Haar Cascade file is loaded correctly
 def load_cascade():
-    face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
-    if face_cascade.empty():
+    # Path to the Haar Cascade file
+    cascade_path = 'haarcascade_frontalface_default.xml'
+
+    # Check if the Haar Cascade file exists
+    if not os.path.exists(cascade_path):
+        st.error("Haar Cascade file not found! Please upload the file.")
         raise Exception("Haar Cascade file not loaded!")
+    
+    # Load the Haar Cascade file
+    face_cascade = cv2.CascadeClassifier(cascade_path)
+    if face_cascade.empty():
+        st.error("Haar Cascade file failed to load.")
+        raise Exception("Haar Cascade file not loaded properly!")
+    
     return face_cascade
 
-# Detect faces
+# Detect faces in the uploaded image
 def detect_faces(image, face_cascade):
+    # Convert the image to grayscale
     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    
+    # Perform face detection
     faces = face_cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5)
+    
+    # Draw rectangles around detected faces
     for (x, y, w, h) in faces:
         cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 2)
+    
     return image, len(faces)
 
-# Streamlit app
+# Main Streamlit app
 def main():
     st.title("Face Detection App")
     st.write("Upload an image, and the app will detect faces!")
 
-    # Load Haar Cascade
-    face_cascade = load_cascade()
+    # Load the Haar Cascade
+    try:
+        face_cascade = load_cascade()
+    except Exception as e:
+        st.error(f"Error: {e}")
+        return
 
-    # File uploader
+    # File uploader for image
     uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])
     if uploaded_file is not None:
         # Save the uploaded image temporarily
@@ -72,44 +56,24 @@ def main():
         with open(img_path, "wb") as f:
             f.write(uploaded_file.getbuffer())
 
-        # Read and process the image
+        # Open the uploaded image and convert it to a NumPy array
         image = np.array(Image.open(uploaded_file))
         image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
 
-        # Detect faces
+        # Detect faces in the image
         result_image, face_count = detect_faces(image, face_cascade)
 
-        # Convert BGR to RGB for display
+        # Convert BGR to RGB for displaying in Streamlit
         result_image = cv2.cvtColor(result_image, cv2.COLOR_BGR2RGB)
 
-        # Display the image with face detection
+        # Display the image with face detection results
         st.image(result_image, caption=f"Detected {face_count} face(s).", use_column_width=True)
 
-        # Show success or failure message based on face count
+        # Display success or failure message
         if face_count > 0:
             st.success("Face Detection Successful!")
         else:
             st.error("No faces detected. Please try again with a clearer image.")
 
-if __name__ == "__main__":
-    main()
-
-
-    # File uploader
-    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])
-    if uploaded_file is not None:
-        # Read the image
-        image = np.array(Image.open(uploaded_file))
-        image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-
-        # Detect faces
-        result_image, face_count = detect_faces(image, face_cascade)
-
-        # Convert BGR to RGB for display
-        result_image = cv2.cvtColor(result_image, cv2.COLOR_BGR2RGB)
-
-        # Display the image
-        st.image(result_image, caption=f"Detected {face_count} face(s).", use_column_width=True)
-
 if __name__ == "__main__":
     main()