Update app.py

app.py

@@ -7,7 +7,7 @@ import numpy as np
 import streamlit as st
 from streamlit_webrtc import WebRtcMode, webrtc_streamer
 from sample_utils.turn import get_ice_servers
-from cvzone.HandTrackingModule import HandDetector
+import mediapipe as mp
 import os
 import time
 
@@ -20,8 +20,10 @@ st.title("Interactive Virtual Keyboard")
 st.subheader('''Turn on the webcam and use hand gestures to interact with the virtual keyboard.
 Use 'a' and 'd' from the keyboard to change the background.''')
 
-# Initialize modules
-detector = HandDetector(maxHands=1, detectionCon=0.7)
+# Initialize MediaPipe Hand Detector
+mp_hands = mp.solutions.hands
+hands = mp_hands.Hands(static_image_mode=False, max_num_hands=2, min_detection_confidence=0.7)
+mp_drawing = mp.solutions.drawing_utils
 
 # Define virtual keyboard layout
 keys = [["Q", "W", "E", "R", "T", "Y", "U", "I", "O", "P"],
@@ -35,7 +37,7 @@ class Detection(NamedTuple):
 
 result_queue: "queue.Queue[List[Detection]]" = queue.Queue()
 
-# Background image loading
+# Load background images
 listImg = os.listdir('model/street') if os.path.exists('model/street') else []
 if not listImg:
     st.error("Error: 'street' directory is missing or empty. Please add background images.")
@@ -54,21 +56,34 @@ if "output_text" not in st.session_state:
 def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
     global indexImg, output_text
 
-    # Convert the frame to BGR
     img = frame.to_ndarray(format="bgr24")
+    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
-    # Process the frame with Hand Detector
-    hands, img = detector.findHands(img, draw=True)
+    # Process the frame with MediaPipe
+    result = hands.process(img_rgb)
 
     detections = []
-    if hands:
-        logger.info(f"Detected {len(hands)} hand(s).")
-        for hand in hands:
-            bbox = hand['bbox']
-            label = "Hand"
-            score = hand['score']
-            box = np.array([bbox[0], bbox[1], bbox[0] + bbox[2], bbox[1] + bbox[3]])
-            detections.append(Detection(label=label, score=score, box=box))
+    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.DrawingSpec(color=(0, 255, 0), thickness=2, circle_radius=4),
+                mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=2)
+            )
+            # Extract bounding box for detection info
+            x_min, y_min = 1.0, 1.0
+            x_max, y_max = 0.0, 0.0
+            for lm in hand_landmarks.landmark:
+                x_min = min(x_min, lm.x)
+                y_min = min(y_min, lm.y)
+                x_max = max(x_max, lm.x)
+                y_max = max(y_max, lm.y)
+            
+            h, w, _ = img.shape
+            bbox = np.array([int(x_min * w), int(y_min * h), int((x_max - x_min) * w), int((y_max - y_min) * h)])
+            detections.append(Detection(label="Hand", score=1.0, box=bbox))
+            
+        logger.info(f"Detected {len(detections)} hand(s).")
     else:
         logger.info("No hands detected.")