Update app.py

app.py

@@ -8,12 +8,9 @@ def reconstruct_shape(image):
         
     # Check if the image has an alpha (transparency) channel
     if image.shape[2] == 4:
-        # Use the alpha channel to create a mask of the object
         mask = image[:, :, 3]
-        # Get the color channels (RGB)
         color_img = image[:, :, :3]
     else:
-        # If no alpha channel, assume a white or black background and threshold
         gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
         _, mask = cv2.threshold(gray, 10, 255, cv2.THRESH_BINARY)
         color_img = image
@@ -22,66 +19,66 @@ def reconstruct_shape(image):
     contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
     
     if not contours:
-        return image # Return original if no shape is found
+        return image 
 
     # Find the largest contour (the main object)
     c = max(contours, key=cv2.contourArea)
     
-    # Extract the average color of the original shape
+    # Extract the average color of the original shape for the reconstructed parts
     mean_val = cv2.mean(color_img, mask=mask)
-    dominant_color = (int(mean_val[0]), int(mean_val[1]), int(mean_val[2]), 255) # RGBA
+    # Make the reconstructed part slightly distinct, or keep it exactly the average color
+    dominant_color = (int(mean_val[0]), int(mean_val[1]), int(mean_val[2]), 255) 
 
     # --- Shape Classification ---
-    # Calculate bounding rectangle
     x, y, w, h = cv2.boundingRect(c)
     rect_area = w * h
     
-    # Calculate minimum enclosing circle
     (cx, cy), radius = cv2.minEnclosingCircle(c)
     circle_area = np.pi * (radius ** 2)
-    
-    # Actual contour area
     contour_area = cv2.contourArea(c)
     
-    # Determine which regular shape fits better by comparing area ratios
-    # The one with the ratio closer to 1 is the likely original shape
     rect_ratio = contour_area / rect_area if rect_area > 0 else 0
     circle_ratio = contour_area / circle_area if circle_area > 0 else 0
 
-    # Create a blank transparent canvas of the same size
+    # Create a blank transparent canvas for the output
     output_image = np.zeros((image.shape[0], image.shape[1], 4), dtype=np.uint8)
 
-    # --- Shape Reconstruction ---
+    # --- Step 1: Draw the Reconstructed Base Shape ---
     if circle_ratio > rect_ratio:
-        # Reconstruct as a Circle
         center = (int(cx), int(cy))
         cv2.circle(output_image, center, int(radius), dominant_color, -1)
-        shape_detected = "Circle"
     else:
-        # Reconstruct as a Rectangle/Square
-        # Check if it's close to a square
         if 0.85 <= w / h <= 1.15:
-            # Make it a perfect square
             side = max(w, h)
             cv2.rectangle(output_image, (x, y), (x + side, y + side), dominant_color, -1)
-            shape_detected = "Square"
         else:
             cv2.rectangle(output_image, (x, y), (x + w, y + h), dominant_color, -1)
-            shape_detected = "Rectangle"
+
+    # --- Step 2: Paste the Original Image Over the Base ---
+    # This keeps the original texture intact while the missing parts show the dominant color
+    original_area = mask > 0
+    output_image[original_area] = image[original_area]
+
+    # --- Step 3: Draw the "Crack" / Seam ---
+    # Draw a dark line along the boundary of the original shape to show where it was reconstructed
+    crack_color = (40, 40, 40, 255) # Dark gray/black line for the crack
+    crack_thickness = 3 # Adjust thickness of the line here
+    
+    cv2.drawContours(output_image, [c], -1, crack_color, crack_thickness)
 
     return output_image
 
 # --- Gradio Interface Setup ---
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🔷 Irregular to Regular Shape Reconstructor")
-    gr.Markdown("Upload an image of an irregular shape with missing parts (preferably with a transparent background). The algorithm will detect if it was originally a rectangle, square, or circle, and reconstruct its full geometric shape matching the original color.")
+    gr.Markdown("# 🔷 Irregular Shape Reconstructor (With Visible Seams)")
+    gr.Markdown("Upload an image of an irregular shape. The algorithm reconstructs its original geometric form and draws a visible 'crack' line to show exactly where the new parts were glued on.")
     
     with gr.Row():
         with gr.Column():
             input_image = gr.Image(label="Upload Irregular Shape", image_mode="RGBA", type="numpy")
             submit_btn = gr.Button("Reconstruct Shape", variant="primary")
         with gr.Column():
-            output_image = gr.Image(label="Reconstructed Regular Shape", image_mode="RGBA")
+            output_image = gr.Image(label="Reconstructed Shape with Crack", image_mode="RGBA")
             
     submit_btn.click(fn=reconstruct_shape, inputs=input_image, outputs=output_image)