update app.py v1

app.py

@@ -2,49 +2,39 @@ import gradio as gr
 import numpy as np
 import cv2
 import torch
-import torchvision.transforms as transforms
-from fer import FER
-import librosa
-from python_speech_features import mfcc
 import pandas as pd
 from datetime import datetime
 import time
 from transformers import pipeline
+from deepface import DeepFace
+import librosa
+from python_speech_features import mfcc
 
 # Initialize models
-emotion_detector = FER(mtcnn=True)  # Facial expression recognition
 voice_classifier = pipeline("audio-classification", model="superb/hubert-base-superb-er")
 
 # Global variables to store results
 emotion_history = []
-current_emotions = {"face": "Neutral", "voice": "Neutral"}
+current_emotions = {"face": "neutral", "voice": "neutral"}
 last_update_time = time.time()
 
-# Preprocessing for face detection
-transform = transforms.Compose([
-    transforms.ToPILImage(),
-    transforms.Resize((48, 48)),
-    transforms.Grayscale(),
-    transforms.ToTensor(),
-])
-
 def analyze_face(frame):
-    """Analyze facial expressions in the frame"""
+    """Analyze facial expressions in the frame using DeepFace"""
     try:
-        # Convert frame to RGB (FER expects RGB)
+        # Convert frame to RGB (DeepFace expects RGB)
         rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
         
         # Detect emotions
-        results = emotion_detector.detect_emotions(rgb_frame)
+        result = DeepFace.analyze(rgb_frame, actions=['emotion'], enforce_detection=False)
         
-        if results:
-            emotions = results[0]['emotions']
+        if result and isinstance(result, list):
+            emotions = result[0]['emotion']
             dominant_emotion = max(emotions, key=emotions.get)
             return dominant_emotion, emotions
-        return "Neutral", {"angry": 0, "disgust": 0, "fear": 0, "happy": 0, "sad": 0, "surprise": 0, "neutral": 1}
+        return "neutral", {"angry": 0, "disgust": 0, "fear": 0, "happy": 0, "sad": 0, "surprise": 0, "neutral": 1}
     except Exception as e:
         print(f"Face analysis error: {e}")
-        return "Neutral", {"angry": 0, "disgust": 0, "fear": 0, "happy": 0, "sad": 0, "surprise": 0, "neutral": 1}
+        return "neutral", {"angry": 0, "disgust": 0, "fear": 0, "happy": 0, "sad": 0, "surprise": 0, "neutral": 1}
 
 def analyze_voice(audio):
     """Analyze voice tone from audio"""
@@ -117,10 +107,10 @@ def get_practitioner_advice(face_emotion, voice_emotion):
         advice.append("Patient appears distressed. Consider speaking more slowly and with reassurance.")
     elif face_emotion == "angry":
         advice.append("Patient seems frustrated. Acknowledge their concerns and maintain calm demeanor.")
-    elif face_emotion == "confused":
-        advice.append("Patient may not understand. Consider rephrasing or providing more explanation.")
-    elif face_emotion == "pain":
-        advice.append("Patient appears to be in pain. Consider asking about discomfort.")
+    elif face_emotion == "disgust":
+        advice.append("Patient may be uncomfortable. Check if they're experiencing any discomfort.")
+    elif face_emotion == "surprise":
+        advice.append("Patient seems surprised. Ensure they understand all information.")
     
     # Voice emotion advice
     if voice_emotion in ["sad", "fear"]:
@@ -140,7 +130,7 @@ def process_input(video, audio):
             frame = cv2.cvtColor(video, cv2.COLOR_RGB2BGR)
             face_emotion, face_details = analyze_face(frame)
         else:
-            face_emotion, face_details = "Neutral", {}
+            face_emotion, face_details = "neutral", {}
         
         # Process audio
         if audio is not None:
@@ -212,8 +202,4 @@ with gr.Blocks(title="Patient Emotion Recognition", theme="soft") as demo:
     submit_btn.click(
         process_input,
         inputs=[video_input, audio_input],
-        outputs=[current_face, current_voice, timeline_output, advice_output, face_details, voice_details]
-    )
-
-if __name__ == "__main__":
-    demo.launch(debug=True)
+