Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import pytesseract
+import cv2
+
+def extract_text(image):
+  """
+  Extracts text from an uploaded image using PyTesseract.
+
+  Args:
+      image: A PIL Image object or OpenCV image array containing the bill or document.
+
+  Returns:
+      str: The extracted text from the image.
+  """
+
+  # Handle potential errors gracefully
+  try:
+    # Preprocess the image for better text recognition (optional)
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
+
+    # Use PyTesseract for text extraction
+    text = pytesseract.image_to_string(thresh, config='--psm 6')  # Optimize for single block text
+    return text
+  except Exception as e:
+    return f"Error: {e}"  # Informative error message
+
+# Gradio interface for user interaction
+iface = gr.Interface(
+    fn=extract_text,
+    inputs=gr.File(label="Upload Bill/Document (Image)"),
+    outputs=gr.Textbox(label="Extracted Text"),
+    title="Text Extractor for Bills and Documents",
+    description="Upload your bill or document to extract the text content.",
+)
+
+# Launch the Gradio app
+iface.launch()