Update app.py

app.py

@@ -2,7 +2,6 @@ import streamlit as st
 import cv2
 import numpy as np
 from PIL import Image
-from fer import FER  
 
 # Set the page config
 st.set_page_config(page_title="Emotion Recognition App", layout="centered")
@@ -12,8 +11,15 @@ st.title("Emotion Recognition App")
 # Upload an image
 uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
-# Load FER emotion detection model
-emotion_detector = FER(mtcnn=True)  # Use MTCNN for better face detection
+# Load OpenCV's face detection model
+face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
+
+# Load ONNX emotion detection model
+emotion_model_path = "emotion_recognition.onnx"  # Replace with your model path
+emotion_net = cv2.dnn.readNetFromONNX(emotion_model_path)
+
+# Emotion labels (based on model documentation)
+emotion_labels = ["Angry", "Disgust", "Fear", "Happy", "Sad", "Surprise", "Neutral"]
 
 # Resize image to reduce memory usage
 def resize_image(image, max_size=(800, 800)):
@@ -36,24 +42,31 @@ if uploaded_file is not None:
         # Convert image to numpy array
         image_np = np.array(image)
 
-        # Detect emotions
-        results = emotion_detector.detect_emotions(image_np)
+        # Convert image to grayscale for face detection
+        gray_image = cv2.cvtColor(image_np, cv2.COLOR_RGB2GRAY)
+
+        # Detect faces
+        faces = face_cascade.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
+
+        if len(faces) > 0:
+            for (x, y, w, h) in faces:
+                # Extract face ROI
+                face_roi = image_np[y:y+h, x:x+w]
+                face_blob = cv2.dnn.blobFromImage(face_roi, 1.0, (64, 64), (104, 117, 123), swapRB=True)
 
-        if results:
-            for face in results:
-                # Get bounding box and detected emotion
-                box = face["box"]
-                emotions = face["emotions"]
-                dominant_emotion = max(emotions, key=emotions.get)
+                # Predict emotion
+                emotion_net.setInput(face_blob)
+                predictions = emotion_net.forward()
+                emotion_idx = np.argmax(predictions)
+                emotion = emotion_labels[emotion_idx]
 
-                # Draw a rectangle around the face
-                x, y, w, h = box
+                # Draw rectangle around the face
                 cv2.rectangle(image_np, (x, y), (x+w, y+h), (0, 255, 0), 2)
 
-                # Display detected emotion
+                # Display emotion
                 cv2.putText(
                     image_np,
-                    dominant_emotion,
+                    emotion,
                     (x, y - 10),
                     cv2.FONT_HERSHEY_SIMPLEX,
                     0.9,
@@ -64,4 +77,4 @@ if uploaded_file is not None:
             # Display the processed image
             st.image(image_np, caption="Processed Image", use_column_width=True)
         else:
-            st.warning("No faces detected or unable to determine emotions.")
+            st.warning("No faces detected in the image.")