Improve bounding box for highlight

app.py

@@ -49,25 +49,24 @@ def lift_word_boxes(document):
     return document.context["image"][0][1]
 
 
-def expand_bbox(word_boxes, padding=0.1):
+def expand_bbox(word_boxes):
     if len(word_boxes) == 0:
         return None
 
     min_x, min_y, max_x, max_y = zip(*[x[1] for x in word_boxes])
     min_x, min_y, max_x, max_y = [min(min_x), min(min_y), max(max_x), max(max_y)]
-    if padding != 0:
-        padding = max((max_x - min_x) * padding, (max_y - min_y) * padding)
-        min_x = max(0, min_x - padding)
-        min_y = max(0, min_y - padding)
-        max_x = max_x + padding
-        max_y = max_y + padding
     return [min_x, min_y, max_x, max_y]
 
 
 # LayoutLM boxes are normalized to 0, 1000
-def normalize_bbox(box, width, height):
-    pct = [c / 1000 for c in box]
-    return [pct[0] * width, pct[1] * height, pct[2] * width, pct[3] * height]
+def normalize_bbox(box, width, height, padding=0.005):
+    min_x, min_y, max_x, max_y = [c / 1000 for c in box]
+    if padding != 0:
+        min_x = max(0, min_x - padding)
+        min_y = max(0, min_y - padding)
+        max_x = min(max_x + padding, 1)
+        max_y = min(max_y + padding, 1)
+    return [min_x * width, min_y * height, max_x * width, max_y * height]
 
 
 examples = [