Update app.py

app.py

@@ -46,18 +46,22 @@ def process_image(image, categories_to_hide):
 
     # Expand clothing boundaries if clothes are in `categories_to_hide`
     if "Clothes" in categories_to_hide:
-        clothing_mask = np.isin(mask_data, grouped_mapping["Clothes"]).astype(np.uint8)
+    clothing_mask = np.isin(mask_data, grouped_mapping["Clothes"]).astype(np.uint8)
 
-        # Determine kernel size (3% of the smaller image dimension)
-        height, width = clothing_mask.shape
-        kernel_size = max(1, int(0.02 * min(height, width)))  # Ensure at least 1 pixel
-        kernel = np.ones((kernel_size, kernel_size), np.uint8)
+    # Determine kernel size (2% of the smaller image dimension)
+    height, width = clothing_mask.shape
+    kernel_size = max(1, int(0.02 * min(height, width)))  # Ensure at least 1 pixel
+    kernel = np.ones((kernel_size, kernel_size), np.uint8)
 
-        # Dilate the clothing mask
-        dilated_clothing_mask = cv2.dilate(clothing_mask, kernel, iterations=1)
+    # **Step 1: Fill gaps using Morphological Closing (Dilation + Erosion)**
+    closed_clothing_mask = cv2.morphologyEx(clothing_mask, cv2.MORPH_CLOSE, kernel, iterations=1)
+
+    # **Step 2: Expand clothing boundary using Dilation**
+    dilated_clothing_mask = cv2.dilate(closed_clothing_mask, kernel, iterations=1)
+
+    # Update mask_combined with the expanded clothing mask
+    mask_combined |= (dilated_clothing_mask == 1)
 
-        # Update mask_combined with the expanded clothing mask
-        mask_combined |= (dilated_clothing_mask == 1)
 
     # Apply the mask (preserve only selected regions)
     transparent_image[mask_combined] = image_array[mask_combined]