revert: remove marker column OCR special handling

The HSV-based coloured marker detection caused false positives in
nearly every marker cell. Coloured markers like red "!" are an
extreme edge case — better handled manually in reconstruction.

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

klausur-service/backend/cv_vocab_pipeline.py

@@ -4621,39 +4621,10 @@ def _ocr_single_cell(
                 # in an otherwise empty cell.
                 dark_ratio = float(np.count_nonzero(crop < 180)) / crop.size
                 _run_fallback = dark_ratio > 0.005
-        # For marker columns, also check the colour image — red/coloured
-        # markers appear near-white in grayscale but have high saturation.
-        if not _run_fallback and img_bgr is not None and col.type == 'column_marker':
-            bgr_crop = img_bgr[cell_y:cell_y + cell_h, cell_x:cell_x + cell_w]
-            if bgr_crop.size > 0:
-                hsv = cv2.cvtColor(bgr_crop, cv2.COLOR_BGR2HSV)
-                # Saturation > 80 indicates coloured (non-grey) pixels
-                sat_ratio = float(np.count_nonzero(hsv[:, :, 1] > 80)) / (hsv.shape[0] * hsv.shape[1])
-                if sat_ratio > 0.005:
-                    _run_fallback = True
     if _run_fallback:
-        # For marker columns with coloured content (e.g. red "!"), convert
-        # the BGR crop to a binarized grayscale that preserves saturated pixels.
-        _marker_ocr_img = ocr_img
-        if col.type == 'column_marker' and img_bgr is not None:
-            bgr_crop_full = img_bgr[cell_y:cell_y + cell_h, cell_x:cell_x + cell_w]
-            if bgr_crop_full.size > 0:
-                hsv = cv2.cvtColor(bgr_crop_full, cv2.COLOR_BGR2HSV)
-                # Create mask: either dark (V<180) or saturated (S>60)
-                dark_mask = hsv[:, :, 2] < 180
-                sat_mask = hsv[:, :, 1] > 60
-                combined = dark_mask | sat_mask
-                # Build grayscale: foreground=0 (black), background=255 (white)
-                marker_gray = np.full(combined.shape, 255, dtype=np.uint8)
-                marker_gray[combined] = 0
-                # Place into a full-size image at the crop position
-                _marker_full = np.full_like(ocr_img, 255)
-                _marker_full[cell_y:cell_y + cell_h, cell_x:cell_x + cell_w] = marker_gray
-                _marker_ocr_img = _marker_full
-
         # For narrow columns, upscale the crop before OCR
-        if is_narrow and _marker_ocr_img is not None:
+        if is_narrow and ocr_img is not None:
-            _crop_slice = _marker_ocr_img[cell_y:cell_y + cell_h, cell_x:cell_x + cell_w]
+            _crop_slice = ocr_img[cell_y:cell_y + cell_h, cell_x:cell_x + cell_w]
             _upscaled = _ensure_minimum_crop_size(_crop_slice)
             if _upscaled is not _crop_slice:
                 # Build a temporary full-size image with the upscaled crop
@@ -4682,7 +4653,7 @@ def _ocr_single_cell(
                 )
                 _cell_psm = _select_psm_for_column(col.type, col.width, row.height)
                 cell_lang = lang_map.get(col.type, lang)
-                fallback_words = ocr_region(_marker_ocr_img, cell_region,
+                fallback_words = ocr_region(ocr_img, cell_region,
                                             lang=cell_lang, psm=_cell_psm)
         else:
             cell_region = PageRegion(
@@ -4699,7 +4670,7 @@ def _ocr_single_cell(
             else:
                 _cell_psm = _select_psm_for_column(col.type, col.width, row.height)
                 cell_lang = lang_map.get(col.type, lang)
-                fallback_words = ocr_region(_marker_ocr_img, cell_region,
+                fallback_words = ocr_region(ocr_img, cell_region,
                                             lang=cell_lang, psm=_cell_psm)
 
         if fallback_words:
@@ -4723,7 +4694,7 @@ def _ocr_single_cell(
                 width=cell_w, height=cell_h,
             )
             cell_lang = lang_map.get(col.type, lang)
-            psm7_words = ocr_region(_marker_ocr_img, _fb_region, lang=cell_lang, psm=7)
+            psm7_words = ocr_region(ocr_img, _fb_region, lang=cell_lang, psm=7)
             if psm7_words:
                 psm7_words = [w for w in psm7_words if w.get('conf', 0) >= _MIN_WORD_CONF]
             if psm7_words:
@@ -4768,9 +4739,7 @@ def _ocr_single_cell(
                         used_engine = 'row_strip_rapid'
 
     # --- NOISE FILTER: clear cells that contain only OCR artifacts ---
-    # Skip noise filter for marker columns — they legitimately contain
+    if text.strip():
-    # only punctuation like "!" or "*" which _clean_cell_text would remove.
-    if text.strip() and col.type != 'column_marker':
         text = _clean_cell_text(text)
         if not text:
             avg_conf = 0.0