Update app.py

app.py

@@ -8,7 +8,6 @@ import streamlit as st
 from streamlit_webrtc import WebRtcMode, webrtc_streamer
 from sample_utils.turn import get_ice_servers
 import mediapipe as mp
-from cvzone.SelfiSegmentationModule import SelfiSegmentation
 import os
 import time
 
@@ -21,11 +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 MediaPipe and Background Segmentor
+# Initialize MediaPipe Hand Detection
 mp_hands = mp.solutions.hands
-hands = mp_hands.Hands(static_image_mode=False, max_num_hands=2, min_detection_confidence=0.7)
+hands = mp_hands.Hands(max_num_hands=1, min_detection_confidence=0.5)
 mp_drawing = mp.solutions.drawing_utils
-segmentor = SelfiSegmentation()
 
 # Virtual Keyboard Layout
 keys = [["Q", "W", "E", "R", "T", "Y", "U", "I", "O", "P"],
@@ -45,15 +43,6 @@ class Detection(NamedTuple):
 
 result_queue: "queue.Queue[List[Detection]]" = queue.Queue()
 
-# 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.")
-    st.stop()
-else:
-    imgList = [cv2.imread(f'model/street/{imgPath}') for imgPath in listImg]
-    imgList = [img for img in imgList if img is not None]
-
 indexImg = 0
 output_text = ""
 prev_key_time = [time.time()] * 2
@@ -61,30 +50,32 @@ prev_key_time = [time.time()] * 2
 if "output_text" not in st.session_state:
     st.session_state["output_text"] = ""
 
-# Video Frame Callback with Your Logic
+# Video Frame Callback with Logic Correction
 def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
     global indexImg, output_text
 
     img = frame.to_ndarray(format="bgr24")
-    imgOut = segmentor.removeBG(img, imgList[indexImg])
 
     # Process frame using MediaPipe
-    result = hands.process(cv2.cvtColor(imgOut, cv2.COLOR_BGR2RGB))
+    result = hands.process(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
 
-    buttonList = [Button([30 + col * 105, 30 + row * 120], key) for row, line in enumerate(keys) for col, key in enumerate(line)]
+    # Create Buttons
+    buttonList = [Button([30 + col * 105, 30 + row * 120], key) 
+                  for row, line in enumerate(keys) 
+                  for col, key in enumerate(line)]
 
     detections = []
     if result.multi_hand_landmarks:
         for hand_landmarks in result.multi_hand_landmarks:
             # Draw hand landmarks
             mp_drawing.draw_landmarks(
-                imgOut, hand_landmarks, mp_hands.HAND_CONNECTIONS,
+                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 each hand
-            h, w, _ = imgOut.shape
+            h, w, _ = img.shape
             x_min, y_min = w, h
             x_max, y_max = 0, 0
             for lm in hand_landmarks.landmark:
@@ -101,7 +92,7 @@ def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
             x8, y8 = int(hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * w), \
                      int(hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * h)
             
-            # Distance Calculation
+            # Calculate Distance and Detect Button Click
             distance = np.sqrt((x8 - x4) ** 2 + (y8 - y4) ** 2)
             click_threshold = 50
 
@@ -109,10 +100,10 @@ def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
                 x, y = button.pos
                 w, h = button.size
                 if x < x8 < x + w and y < y8 < y + h:
-                    cv2.rectangle(imgOut, button.pos, (x + w, y + h), (0, 255, 160), -1)
-                    cv2.putText(imgOut, button.text, (x + 20, y + 70), cv2.FONT_HERSHEY_PLAIN, 5, (255, 255, 255), 3)
+                    cv2.rectangle(img, button.pos, (x + w, y + h), (0, 255, 160), -1)
+                    cv2.putText(img, button.text, (x + 20, y + 70), cv2.FONT_HERSHEY_PLAIN, 5, (255, 255, 255), 3)
 
-                    # Simulate key press if finger close enough
+                    # Simulate Key Press if Finger Close Enough
                     if (distance / np.sqrt(bbox[2] ** 2 + bbox[3] ** 2)) * 100 < click_threshold:
                         if time.time() - prev_key_time[0] > 2:
                             prev_key_time[0] = time.time()
@@ -125,7 +116,7 @@ def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
 
     result_queue.put(detections)
     st.session_state["output_text"] = output_text
-    return av.VideoFrame.from_ndarray(imgOut, format="bgr24")
+    return av.VideoFrame.from_ndarray(img, format="bgr24")
 
 # WebRTC Streamer
 webrtc_streamer(