feat: add AI detection overlay visualization with bounding boxes on extracted entities

README.md

@@ -432,7 +432,7 @@ MIT License - See LICENSE file for details
 **Soumyajit Ghosh** - 3rd Year BTech Student
 
 - Exploring AI/ML and practical applications
-- [LinkedIn](https://www.linkedin.com/in/soumyajit-ghosh-tech) | [GitHub](https://github.com/GSoumyajit2005) | [Portfolio](#) (Coming Soon)
+- [LinkedIn](https://www.linkedin.com/in/soumyajit-ghosh-tech) | [GitHub](https://github.com/GSoumyajit2005) | [Portfolio](https://soumyajitghosh.vercel.app)
 
 ---
 

app.py

@@ -3,7 +3,7 @@ import os
 import json
 from datetime import datetime
 from pathlib import Path
-from PIL import Image
+from PIL import Image, ImageDraw
 import pandas as pd
 import sys
 
@@ -147,6 +147,28 @@ with tab1:
 
                     st.success("Extraction Complete")
 
+                    # --- AI Detection Overlay Visualization ---
+                    raw_predictions = result.get("raw_predictions")
+                    if raw_predictions and uploaded_file.type != "application/pdf":
+                        # Reload the original image for annotation
+                        uploaded_file.seek(0)
+                        overlay_image = Image.open(uploaded_file).convert("RGB")
+                        draw = ImageDraw.Draw(overlay_image)
+
+                        # Draw red rectangles around each detected entity's bounding boxes
+                        for entity_name, entity_data in raw_predictions.items():
+                            bboxes = entity_data.get("bbox", [])
+                            for box in bboxes:
+                                # bbox format: [x, y, width, height]
+                                x, y, w, h = box
+                                draw.rectangle(
+                                    [x, y, x + w, y + h],
+                                    outline="red",
+                                    width=2
+                                )
+
+                        st.image(overlay_image, caption="AI Detection Overlay", use_container_width=True)
+
                 except Exception as e:
                     st.error(f"Pipeline error: {e}")
 

src/ml_extraction.py

@@ -126,7 +126,8 @@ def extract_ml_based(image_path: str) -> Dict[str, Any]:
         "bill_to": extracted_entities.get("BILL_TO", {}).get("text"),
         "total_amount": None, 
         "items": [],
-        "raw_text": raw_text
+        "raw_text": raw_text,
+        "raw_predictions": extracted_entities  # Contains text and bbox data for each entity
     }
 
     # Fallbacks

src/pipeline.py

@@ -129,6 +129,12 @@ def process_invoice(image_path: str,
                 error_list.append(f"{field}: {msg}")
 
             final_data['validation_errors'] = error_list
+        
+        # Preserve raw_predictions and raw_text for UI visualization (not in schema)
+        if 'raw_predictions' in raw_result:
+            final_data['raw_predictions'] = raw_result['raw_predictions']
+        if 'raw_text' in raw_result:
+            final_data['raw_text'] = raw_result['raw_text']
 
     # --- DUPLICATE DETECTION ---
     # We calculate the hash based on the final (or raw) data.