Update app.py

app.py

@@ -1,121 +1,61 @@
+# Sign Language Translator with Streamlit
+
 import streamlit as st
 import cv2
 import numpy as np
-import base64
-
-# Function to convert text to image
-def text_to_image(text, width=400, height=200, font_size=0.7, font_color=(0, 0, 0), bg_color=(255, 255, 255)):
-    # Create a blank image with white background
-    image = np.zeros((height, width, 3), dtype=np.uint8)
-    image[:, :] = bg_color
-
-    # Put text on the image using OpenCV
-    font = cv2.FONT_HERSHEY_SIMPLEX
-    text_size, _ = cv2.getTextSize(text, font, font_size, 2)
-    text_x = (width - text_size[0]) // 2
-    text_y = (height + text_size[1]) // 2
-    cv2.putText(image, text, (text_x, text_y), font, font_size, font_color, 2, cv2.LINE_AA)
-
-    return image
-
-# Function to detect open palm gesture
-def detect_gesture(frame):
-    # Convert frame to grayscale
-    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
-    
-    # Use median blur for noise reduction
-    gray = cv2.medianBlur(gray, 5)
-    
-    # Thresholding
-    _, threshold = cv2.threshold(gray, 130, 255, cv2.THRESH_BINARY_INV)
-    
-    # Find contours in the thresholded image
-    contours, _ = cv2.findContours(threshold.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
-    
-    # Find the largest contour (likely the hand)
-    if len(contours) > 0:
-        hand_contour = max(contours, key=cv2.contourArea)
-        hull = cv2.convexHull(hand_contour)
-        defects = cv2.convexityDefects(hand_contour, cv2.convexHull(hand_contour, returnPoints=False))
-        
-        finger_count = 0
-        
-        # Count fingers based on convex defects
-        for i in range(defects.shape[0]):
-            s, e, f, d = defects[i][0]
-            start = tuple(hand_contour[s][0])
-            end = tuple(hand_contour[e][0])
-            far = tuple(hand_contour[f][0])
-            
-            a = np.sqrt((end[0] - start[0])**2 + (end[1] - start[1])**2)
-            b = np.sqrt((far[0] - start[0])**2 + (far[1] - start[1])**2)
-            c = np.sqrt((end[0] - far[0])**2 + (end[1] - far[1])**2)
-            
-            angle = np.arccos((b**2 + c**2 - a**2) / (2 * b * c)) * 57
-            
-            if angle <= 90:
-                finger_count += 1
-                
-        finger_count += 1
-    
-        # Define gestures based on finger count
-        if finger_count == 1:
-            return "Thumbs Up"
-        elif finger_count == 2:
-            return "Two Fingers"
-        elif finger_count == 5:
-            return "Open Palm"
-        else:
-            return "Not Recognized"
-    
-    return "No Hand Detected"
-
-# Streamlit App
-st.title("Gesture Recognition and Sign Language Translator")
-
-# Checkbox to choose the functionality
-use_gesture = st.sidebar.checkbox("Do you know Sign Language?")
-
-if use_gesture:
-    st.write("This section detects basic gestures using a webcam.")
-    st.write("Please make sure your webcam is accessible.")
-    
-    # Open webcam
-    cam = cv2.VideoCapture(0)
-    
-    if not cam.isOpened():
-        st.write("Error: Could not open webcam.")
-    else:
-        frame_placeholder = st.empty()
-        
-        while True:
-            ret, frame = cam.read()
-            if not ret:
-                st.write("Error: Could not read frame.")
-                break
-            
-            gesture = detect_gesture(frame)
-            cv2.putText(frame, f"Gesture: {gesture}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)
-            
-            # Convert OpenCV image to format suitable for Streamlit
-            _, buffer = cv2.imencode('.jpg', frame)
-            frame_base64 = base64.b64encode(buffer.getvalue()).decode('utf-8')
-            img_str = f"data:image/jpeg;base64,{frame_base64}"
-            
-            # Display the frame
-            frame_placeholder.markdown(f'<img src="{img_str}" style="width: 100%;">', unsafe_allow_html=True)
-            
-            if st.button("Stop Webcam", key="stop_webcam"):
-                break
-        
-        # Release webcam
-        cam.release()
-else:
-    st.write("Enter the text that you want to show to people who don't know sign language.")
-    text_input = st.text_input("Enter text:")
-
-    if st.button("Convert Text to Image"):
-        generated_image = text_to_image(text_input)
-        st.image(generated_image, caption="Generated Image from Text", use_column_width=True)
-
-st.write("Thanks for using our Sign Language Assistant!")
+import mediapipe as mp
+
+# Load Mediapipe Hands model
+mp_hands = mp.solutions.hands
+hands = mp_hands.Hands()
+
+# Function to process webcam feed
+def process_webcam():
+    cap = cv2.VideoCapture(0)
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # Convert the frame to RGB
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        results = hands.process(frame_rgb)
+
+        # Draw hand landmarks
+        if results.multi_hand_landmarks:
+            for hand_landmarks in results.multi_hand_landmarks:
+                mp.solutions.drawing_utils.draw_landmarks(frame, hand_landmarks, mp_hands.HAND_CONNECTIONS)
+
+        # Display the frame
+        cv2.imshow('Webcam', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+# Streamlit UI
+st.title("Sign Language Translator")
+st.write("This application translates sign language into Farsi and provides visual aids for understanding.")
+
+if st.button("Open Webcam"):
+    st.write("Opening webcam...")
+    process_webcam()
+
+# Placeholder for translation logic
+def translate_sign_language(hand_gesture):
+    # Placeholder for actual translation logic
+    return "Translated Text in Farsi"
+
+# Placeholder for visual aid
+def show_visual_aid(hand_gesture):
+    # Placeholder for actual visual aid logic
+    st.image("path_to_hand_shape_image.png", caption="Hand Shape for Sign Language")
+
+# User input for non-sign language users
+user_input = st.text_input("Enter text if you do not know sign language:")
+if user_input:
+    st.write("You entered:", user_input)
+    # Logic to show visual aid
+    show_visual_aid(user_input)