fix: only detect circles and illustrations, drop arrow/icon/line

Text fragments after word exclusion are indistinguishable from arrows
and icons via contour metrics. Since the goal is detecting graphics,
images, boxes and colors (not arrows/icons), simplify to only:
- circle/balloon (circularity > 0.55 — very reliable)
- illustration (area > 3000 — clearly non-text)

Boxes and colors are handled by cv_box_detect and cv_color_detect.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

klausur-service/backend/cv_graphic_detect.py

@@ -101,63 +101,31 @@ def _classify_shape(
 ) -> tuple:
     """Classify contour shape → (shape_name, confidence).
 
-    Uses circularity, aspect ratio, solidity, and vertex count.
-    Only classifies as arrow/circle/line if the element is large enough
-    to be a genuine graphic (not a text fragment).
+    Only detects high-confidence shapes that are clearly non-text:
+    - circle/balloon: high circularity (very reliable)
+    - illustration: large area (clearly a drawing/image)
+
+    Text fragments are classified as 'noise' and filtered out.
+    Boxes and colors are detected by separate modules.
     """
-    aspect = bw / bh if bh > 0 else 1.0
     perimeter = cv2.arcLength(contour, True)
     circularity = (4 * np.pi * area) / (perimeter * perimeter) if perimeter > 0 else 0
-
-    hull = cv2.convexHull(contour)
-    hull_area = cv2.contourArea(hull)
-    solidity = area / hull_area if hull_area > 0 else 0
-
-    # Approximate polygon
-    epsilon = 0.03 * perimeter
-    approx = cv2.approxPolyDP(contour, epsilon, True)
-    vertices = len(approx)
-
+    aspect = bw / bh if bh > 0 else 1.0
     min_dim = min(bw, bh)
-    max_dim = max(bw, bh)
 
-    # --- Circle / balloon --- (check first, most reliable)
-    # Must be reasonably large (not a dot/period) — min 15px
+    # --- Circle / balloon ---
+    # High circularity is the most reliable non-text indicator.
+    # Text characters rarely have circularity > 0.55.
     if circularity > 0.55 and 0.5 < aspect < 2.0 and min_dim > 15:
         conf = min(0.95, circularity)
         return "circle", conf
 
-    # --- Arrow detection --- (strict: must be sizable, distinct shape)
-    # Arrows must be at least 20px in both dimensions
-    if (min_dim > 20 and max_dim > 30
-            and 5 <= vertices <= 9
-            and 0.35 < solidity < 0.80
-            and circularity < 0.35):
-        hull_idx = cv2.convexHull(contour, returnPoints=False)
-        if len(hull_idx) >= 4:
-            try:
-                defects = cv2.convexityDefects(contour, hull_idx)
-                if defects is not None and len(defects) >= 2:
-                    max_depth = max(d[0][3] for d in defects) / 256.0
-                    if max_depth > min_dim * 0.25:
-                        return "arrow", min(0.75, 0.5 + max_depth / max_dim)
-            except cv2.error:
-                pass
-
-    # --- Line (decorative rule, separator) ---
-    # Must be long enough to not be a dash/hyphen
-    if (aspect > 6.0 or aspect < 1 / 6.0) and max_dim > 40:
-        return "line", 0.7
-
-    # --- Larger illustration (drawing, image) ---
+    # --- Illustration (drawing, image, large graphic) ---
+    # Large connected regions that survived word exclusion = genuine graphics.
     if area > 3000 and min_dim > 30:
         return "illustration", 0.6
 
-    # --- Generic icon (moderate size, non-text shape) ---
-    if area > 500 and min_dim > 15:
-        return "icon", 0.4
-
-    # Everything else is too small or text-like — skip
+    # Everything else is likely a text fragment — skip
     return "noise", 0.0