Create app.py

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+from paddleocr import PaddleOCR, draw_ocr
+from PIL import Image, ImageFont
+import numpy as np
+from langdetect import detect
+import os
+
+# Set up OCR for Urdu
+ocr = PaddleOCR(lang='ar')  # Use 'ar' for Arabic-based scripts like Urdu
+
+# Upload or capture image
+st.title("OCR Application for Urdu Text")
+uploaded_file = st.file_uploader("Upload an image", type=["png", "jpg", "jpeg"])
+if uploaded_file is not None:
+    image = Image.open(uploaded_file)
+    st.image(image, caption='Uploaded Image', use_container_width=True)
+    
+    # OCR and Display
+    st.write("Processing...")
+    result = ocr.ocr(np.array(image), cls=True)
+    
+    # Process OCR results
+    boxes = [res[0] for res in result[0]]
+    texts = [res[1][0] for res in result[0]]
+    scores = [res[1][1] for res in result[0]]
+    
+    # Display OCR text results
+    detected_text = " ".join(texts)
+    st.write("Detected Text")
+    st.write(detected_text)
+    
+    # Language detection
+    detected_lang = detect(detected_text)
+    st.write("Detected Language:", detected_lang)
+
+    # Font setup
+    font_path = "/content/drive/MyDrive/Colab Notebooks/NOORIN59.TTF"  # Update with an Urdu-compatible font if possible
+    if not os.path.exists(font_path):
+        st.write("Font file not found. Using default.")
+    
+    # Draw OCR results on image
+    st.write("OCR Visualization")
+    visualized_image = draw_ocr(np.array(image), boxes, texts, scores, font_path=font_path)
+    st.image(visualized_image, caption='OCR Result Visualization', use_container_width=True)
+
+