Update app.py

app.py

@@ -1,22 +1,16 @@
 import streamlit as st
-import cv2
-import mediapipe as mp
 import numpy as np
 import tensorflow as tf
-import tempfile
+from PIL import Image
 from transformers import AutoImageProcessor, AutoModelForImageClassification
 
 # Load gesture classification model from Hugging Face Hub (public model)
 processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224-in21k")
 model = AutoModelForImageClassification.from_pretrained("google/vit-base-patch16-224-in21k")
 
-# Mediapipe initialization
-mp_hands = mp.solutions.hands
-hands = mp_hands.Hands()
-mp_draw = mp.solutions.drawing_utils
-
 # Function for gesture classification
 def classify_gesture(image):
+    image = image.convert("RGB")
     inputs = processor(images=image, return_tensors="pt")
     outputs = model(**inputs)
     prediction = outputs.logits.argmax(-1).item()
@@ -26,40 +20,32 @@ def classify_gesture(image):
 def main():
     st.set_page_config(page_title="Sign Language Translator", layout="wide")
     st.title("🤟 Sign Language Translator")
-    st.write("Translate sign language gestures into text and speech in real time.")
+    st.write("Translate sign language gestures into text and speech.")
 
     # Sidebar
     st.sidebar.header("Settings")
     use_camera = st.sidebar.checkbox("Use Camera")
 
-    # Display Video Feed
-    if use_camera:
-        st.write("### 📸 Live Camera Feed")
-        frame_placeholder = st.empty()
-
-        cap = cv2.VideoCapture(0)
-        while cap.isOpened():
-            ret, frame = cap.read()
-            if not ret:
-                break
-
-            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-            results = hands.process(frame)
-
-            if results.multi_hand_landmarks:
-                for hand_landmarks in results.multi_hand_landmarks:
-                    mp_draw.draw_landmarks(frame, hand_landmarks, mp_hands.HAND_CONNECTIONS)
+    # Upload image
+    uploaded_image = st.file_uploader("Upload an image of a hand gesture", type=["png", "jpg", "jpeg"])
 
-                    # Gesture classification
-                    gesture = classify_gesture(frame)
-                    st.write(f"Gesture: {gesture}")
-
-            frame_placeholder.image(frame, channels="RGB")
-
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-
-        cap.release()
+    # Camera input
+    if use_camera:
+        st.write("### 📸 Capture Gesture Using Camera")
+        camera_image = st.camera_input("Take a picture")
+
+        if camera_image:
+            image = Image.open(camera_image)
+            st.image(image, caption="Captured Image", use_column_width=True)
+            gesture = classify_gesture(image)
+            st.write(f"Gesture: {gesture}")
+
+    # Display uploaded image
+    if uploaded_image:
+        image = Image.open(uploaded_image)
+        st.image(image, caption="Uploaded Image", use_column_width=True)
+        gesture = classify_gesture(image)
+        st.write(f"Gesture: {gesture}")
 
 if __name__ == "__main__":
     main()