Update app.py

app.py

@@ -17,32 +17,41 @@ EMOTIONS = ['neutral', 'happiness', 'surprise', 'sadness', 'anger', 'disgust', '
 # face_detector_mtcnn = MTCNN()
 classifier = load_model(emotion_model_path)
 
-def predict_emotion(image):
-    # Convert the image to grayscale
-    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
-
-    # Detect faces in the grayscale image
+def predict_emotion(frame):
+    frame = imutils.resize(frame, width=300)
+    gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
     faces = face_detection.detectMultiScale(gray, scaleFactor=1.1,
                                             minNeighbors=5, minSize=(30, 30),
                                             flags=cv2.CASCADE_SCALE_IMAGE)
 
-    confidences = {}
-    for (x, y, w, h) in faces:
-        # Extract the region of interest (ROI)
-        roi_gray = gray[y:y+h, x:x+w]
-        roi_gray = cv2.resize(roi_gray, (48, 48), interpolation=cv2.INTER_AREA)
+    frame_clone = frame.copy()
+    if len(faces) > 0:
+        faces = sorted(faces, reverse=True,
+                       key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
+        (fX, fY, fW, fH) = faces
+        
+        # Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
+        # the ROI for classification via the CNN
+        roi = gray[fY:fY + fH, fX:fX + fW]
+        roi = cv2.resize(roi, (48, 48))
+        roi = roi.astype("float") / 255.0
+        roi = img_to_array(roi)
+        roi = np.expand_dims(roi, axis=0)
 
-        # Preprocess the ROI for prediction
-        img = roi_gray.astype('float') / 255.0
-        img = img_to_array(img)
-        img = np.expand_dims(img, axis=0)
+        preds = emotion_classifier.predict(roi)[0]
+        label = EMOTIONS[preds.argmax()]
 
-        # Make a prediction for the emotion
-        prediction = emotion_classifier.predict(img)[0]
-        confidences = {EMOTIONS[i]: float(prediction[i]) for i in range(len(EMOTIONS))}
+        # Overlay a box over the detected face
+        cv2.putText(frame_clone, label, (fX, fY - 10),
+                    cv2.FONT_HERSHEY_DUPLEX, 1, (238, 164, 64), 1)
+        cv2.rectangle(frame_clone, (fX, fY), (fX + fW, fY + fH),
+                      (238, 164, 64), 2)
 
-    return confidences
+    else:
+        label = "Can't find your face"
 
+    probs = {emotion: float(prob) for emotion, prob in zip(EMOTIONS, preds)}
+    return frame_clone, probs