Update app.py

app.py

@@ -1,51 +1,32 @@
 import gradio as gr
-from PIL import Image
 import pytesseract
-import re
+from PIL import Image
+import json
 
-def extract_kyc_fields(image):
+def extract_fields(image):
     try:
-        text = pytesseract.image_to_string(image)
-
+        # Extract text using Tesseract
+        raw_text = pytesseract.image_to_string(image)
+        lines = raw_text.split('\n')
         result = {}
 
-        # Aadhaar number pattern
-        aadhaar_match = re.search(r'\d{4}[\s-]?\d{4}[\s-]?\d{4}', text)
-        if aadhaar_match:
-            aadhaar_number = aadhaar_match.group().replace(" ", "-")
-            result["aadhaar_number"] = aadhaar_number
-        else:
-            result["aadhaar_number"] = "Not found"
-
-        # Name (first all-alphabetic line with 2+ words)
-        lines = text.split('\n')
         for line in lines:
-            clean_line = line.strip()
-            if clean_line and re.match(r'^[A-Za-z ]+$', clean_line) and len(clean_line.split()) >= 2:
-                result["name"] = clean_line
-                break
-        if "name" not in result:
-            result["name"] = "Not found"
+            if ':' in line:
+                parts = line.split(':', 1)
+                key = parts[0].strip()
+                value = parts[1].strip()
+                result[key] = value
 
-        # DOB or Birth Date
-        dob_match = re.search(r'(\d{2}[/-]\d{2}[/-]\d{4})|(\d{4}-\d{2}-\d{2})', text)
-        if dob_match:
-            result["dob"] = dob_match.group()
-        else:
-            result["dob"] = "Not found"
+        # Return as pretty JSON
+        return json.dumps(result, indent=2)
 
-        return result
     except Exception as e:
         return {"error": str(e)}
 
-# Gradio UI
-iface = gr.Interface(
-    fn=extract_kyc_fields,
+gr.Interface(
+    fn=extract_fields,
     inputs=gr.Image(type="pil"),
     outputs="json",
-    title="🧠 Smart KYC OCR Extractor",
-    description="Upload Aadhaar/PAN image and extract KYC fields using Tesseract"
-)
-
-if __name__ == "__main__":
-    iface.launch()
+    title="Smart KYC OCR (Tesseract)",
+    description="Upload Aadhaar or PAN image to extract KYC fields as key-value pairs using Tesseract OCR."
+).launch()