Update app.py

app.py

@@ -2,116 +2,64 @@ import os
 import streamlit as st
 import mediapipe as mp
 import cv2
-import time
 from streamlit_webrtc import webrtc_streamer, VideoTransformerBase
 import av
-from queue import Queue
 
-# MediaPipe components for gesture recognition and hand landmarks
+# Initialize MediaPipe Hands
 mp_hands = mp.solutions.hands
 mp_drawing = mp.solutions.drawing_utils
-mp_drawing_styles = mp.solutions.drawing_styles
-BaseOptions = mp.tasks.BaseOptions
-GestureRecognizer = mp.tasks.vision.GestureRecognizer
-GestureRecognizerOptions = mp.tasks.vision.GestureRecognizerOptions
-GestureRecognizerResult = mp.tasks.vision.GestureRecognizerResult
-VisionRunningMode = mp.tasks.vision.RunningMode
 
 # Path to the gesture recognizer model
-model_path = 'model/gesture_recognizer.task'
+model_path = "model/gesture_recognizer.task"
 if not os.path.exists(model_path):
-    raise FileNotFoundError(f"Model file not found at {model_path}")
+    st.error(f"Model file not found at {model_path}. Please upload it to the correct directory.")
+    st.stop()
 
-# Custom video processor class for handling webcam input
 class VideoProcessor(VideoTransformerBase):
     def __init__(self):
-        self.gesture_queue = Queue()  # Queue to store gesture results
-
-        # Configure the Gesture Recognizer with a callback
-        self.recognizer = GestureRecognizer.create_from_options(
-            GestureRecognizerOptions(
-                base_options=BaseOptions(model_asset_path=model_path),
-                running_mode=VisionRunningMode.LIVE_STREAM,
-                result_callback=self.handle_result,  # Set the result callback
-            )
-        )
+        # Initialize MediaPipe Hands
         self.hands = mp_hands.Hands(
             max_num_hands=2,
             model_complexity=0,
-            min_detection_confidence=0.3,
-            min_tracking_confidence=0.3
+            min_detection_confidence=0.5,
+            min_tracking_confidence=0.5,
         )
 
-    def handle_result(self, result: GestureRecognizerResult, output_image: mp.Image, timestamp_ms: int):
-        # Process the result and add it to the queue
-        gestures = []
-        if result.gestures:
-            for hand_gestures in result.gestures:
-                for gesture in hand_gestures:
-                    gestures.append(f"{gesture.category_name} (Confidence: {gesture.score:.2f})")
-        else:
-            gestures.append("No gestures detected.")
-        
-        self.gesture_queue.put(gestures)
-
     def recv(self, frame):
         img = frame.to_ndarray(format="bgr24")
-        img = cv2.flip(img, 1)  # Flip horizontally
+        img = cv2.flip(img, 1)  # Flip for a mirror effect
         img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
-        # Perform hand landmark detection
-        hand_results = self.hands.process(img_rgb)
-
-        # Perform gesture recognition asynchronously
-        mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=img_rgb)
-        current_time_ms = int(time.time() * 1000)
-        self.recognizer.recognize_async(mp_image, current_time_ms)
+        # Process the frame for hand landmarks
+        result = self.hands.process(img_rgb)
 
-        # Draw hand landmarks on the frame
-        if hand_results.multi_hand_landmarks:
-            for hand_landmarks in hand_results.multi_hand_landmarks:
+        # Draw hand landmarks
+        if result.multi_hand_landmarks:
+            for hand_landmarks in result.multi_hand_landmarks:
                 mp_drawing.draw_landmarks(
-                    img,
-                    hand_landmarks,
-                    mp_hands.HAND_CONNECTIONS,
-                    mp_drawing_styles.get_default_hand_landmarks_style(),
-                    mp_drawing_styles.get_default_hand_connections_style()
-                )
-
-        # Optionally display detected gestures from the queue
-        if not self.gesture_queue.empty():
-            gestures = self.gesture_queue.get()
-            for i, gesture in enumerate(gestures):
-                cv2.putText(
-                    img,
-                    gesture,
-                    (10, 50 + i * 30),
-                    cv2.FONT_HERSHEY_SIMPLEX,
-                    1,
-                    (0, 255, 0),
-                    2,
+                    img, hand_landmarks, mp_hands.HAND_CONNECTIONS
                 )
 
         return av.VideoFrame.from_ndarray(img, format="bgr24")
 
 # Streamlit UI
 st.title("Gesture & Hand Landmark Detection 🚀")
-st.markdown("### Recognize and save hand gestures in real time using MediaPipe and Streamlit WebRTC.")
-
-# Sidebar controls
-st.sidebar.title("Control Panel")
-st.sidebar.markdown("<hr>", unsafe_allow_html=True)
+st.write("This app uses MediaPipe and Streamlit to detect hand landmarks in real-time.")
 
-# Run the Streamlit WebRTC app
-webrtc_streamer(key="gesture-detection", video_processor_factory=VideoProcessor)
+# WebRTC streamer for live video
+webrtc_streamer(
+    key="gesture-detection",
+    video_processor_factory=VideoProcessor,
+    rtc_configuration={"iceServers": [{"urls": ["stun:stun.l.google.com:19302"]}]},
+)
 
 # Footer
-st.sidebar.markdown(
+st.markdown(
     """
     <style>
     .footer {text-align: center; font-size: 12px; color: grey; margin-top: 20px;}
     </style>
-    <p class="footer">Made using Streamlit, MediaPipe & OpenCV</p>
+    <p class="footer">Made with ❤️ using Streamlit & MediaPipe</p>
     """,
     unsafe_allow_html=True,
 )