diff --git a/klausur-service/backend/cv_vocab_pipeline.py b/klausur-service/backend/cv_vocab_pipeline.py
index a35e8d8..6c2d890 100644
--- a/klausur-service/backend/cv_vocab_pipeline.py
+++ b/klausur-service/backend/cv_vocab_pipeline.py
@@ -921,22 +921,15 @@ def analyze_layout(layout_img: np.ndarray, ocr_img: np.ndarray) -> List[PageRegi
             width=w, height=content_h
         ))
 
-    # Add header/footer info
-    if top_y > 10:
-        regions.append(PageRegion(
-            type='header', x=0, y=0,
-            width=w, height=top_y
-        ))
-    if bottom_y < h - 10:
-        regions.append(PageRegion(
-            type='footer', x=0, y=bottom_y,
-            width=w, height=h - bottom_y
-        ))
+    # Add header/footer info (gap-based detection with fallback)
+    _add_header_footer(regions, top_y, bottom_y, w, h, inv=inv)
 
+    has_header = any(r.type == 'header' for r in regions)
+    has_footer = any(r.type == 'footer' for r in regions)
     col_count = len([r for r in regions if r.type.startswith('column')])
     logger.info(f"Layout: {col_count} columns, "
-                f"header={'yes' if top_y > 10 else 'no'}, "
-                f"footer={'yes' if bottom_y < h - 10 else 'no'}")
+                f"header={'yes' if has_header else 'no'}, "
+                f"footer={'yes' if has_footer else 'no'}")
 
     return regions
 
@@ -2076,7 +2069,8 @@ def classify_column_types(geometries: List[ColumnGeometry],
                           img_h: int,
                           bottom_y: int,
                           left_x: int = 0,
-                          right_x: int = 0) -> List[PageRegion]:
+                          right_x: int = 0,
+                          inv: Optional[np.ndarray] = None) -> List[PageRegion]:
     """Classify column types using a 3-level fallback chain.
 
     Level 1: Content-based (language + role scoring)
@@ -2159,20 +2153,20 @@ def classify_column_types(geometries: List[ColumnGeometry],
     regions = _classify_by_content(geometries, lang_scores, role_scores, content_w, content_h)
     if regions is not None:
         logger.info("ClassifyColumns: Level 1 (content-based) succeeded")
-        _add_header_footer(regions, top_y, bottom_y, img_w, img_h)
+        _add_header_footer(regions, top_y, bottom_y, img_w, img_h, inv=inv)
         return _with_margins(ignore_regions + regions)
 
     # --- Level 2: Position + language enhanced ---
     regions = _classify_by_position_enhanced(geometries, lang_scores, content_w, content_h)
     if regions is not None:
         logger.info("ClassifyColumns: Level 2 (position+language) succeeded")
-        _add_header_footer(regions, top_y, bottom_y, img_w, img_h)
+        _add_header_footer(regions, top_y, bottom_y, img_w, img_h, inv=inv)
         return _with_margins(ignore_regions + regions)
 
     # --- Level 3: Pure position fallback (old code, no regression) ---
     logger.info("ClassifyColumns: Level 3 (position fallback)")
     regions = _classify_by_position_fallback(geometries, content_w, content_h)
-    _add_header_footer(regions, top_y, bottom_y, img_w, img_h)
+    _add_header_footer(regions, top_y, bottom_y, img_w, img_h, inv=inv)
     return _with_margins(ignore_regions + regions)
 
 
@@ -2534,12 +2528,127 @@ def _classify_by_position_fallback(geometries: List[ColumnGeometry],
     return regions
 
 
+def _detect_header_footer_gaps(
+    inv: np.ndarray,
+    img_w: int,
+    img_h: int,
+) -> Tuple[Optional[int], Optional[int]]:
+    """Detect header/footer boundaries via horizontal projection gap analysis.
+
+    Scans the full-page inverted image for large horizontal gaps in the top/bottom
+    20% that separate header/footer content from the main body.
+
+    Returns:
+        (header_y, footer_y) — absolute y-coordinates.
+        header_y = bottom edge of header region (None if no header detected).
+        footer_y = top edge of footer region (None if no footer detected).
+    """
+    HEADER_FOOTER_ZONE = 0.20
+    GAP_MULTIPLIER = 2.0
+
+    # Step 1: Horizontal projection over full image width
+    h_proj = np.sum(inv, axis=1).astype(float)
+    h_proj_norm = h_proj / (img_w * 255) if img_w > 0 else h_proj
+
+    # Step 2: Smoothing
+    kernel_size = max(3, img_h // 200)
+    if kernel_size % 2 == 0:
+        kernel_size += 1
+    h_smooth = np.convolve(h_proj_norm, np.ones(kernel_size) / kernel_size, mode='same')
+
+    # Step 3: Gap threshold
+    positive = h_smooth[h_smooth > 0]
+    median_density = float(np.median(positive)) if len(positive) > 0 else 0.01
+    gap_threshold = max(median_density * 0.15, 0.003)
+
+    in_gap = h_smooth < gap_threshold
+    MIN_GAP_HEIGHT = max(3, img_h // 500)
+
+    # Step 4: Collect contiguous gaps
+    raw_gaps: List[Tuple[int, int]] = []
+    gap_start: Optional[int] = None
+    for y in range(len(in_gap)):
+        if in_gap[y]:
+            if gap_start is None:
+                gap_start = y
+        else:
+            if gap_start is not None:
+                gap_height = y - gap_start
+                if gap_height >= MIN_GAP_HEIGHT:
+                    raw_gaps.append((gap_start, y))
+                gap_start = None
+    if gap_start is not None:
+        gap_height = len(in_gap) - gap_start
+        if gap_height >= MIN_GAP_HEIGHT:
+            raw_gaps.append((gap_start, len(in_gap)))
+
+    if not raw_gaps:
+        return None, None
+
+    # Step 5: Compute median gap size and large-gap threshold
+    gap_sizes = [g[1] - g[0] for g in raw_gaps]
+    median_gap = float(np.median(gap_sizes))
+    large_gap_threshold = median_gap * GAP_MULTIPLIER
+
+    # Step 6: Find largest qualifying gap in header / footer zones
+    header_zone_limit = int(img_h * HEADER_FOOTER_ZONE)
+    footer_zone_start = int(img_h * (1.0 - HEADER_FOOTER_ZONE))
+
+    header_y: Optional[int] = None
+    footer_y: Optional[int] = None
+
+    best_header_size = 0
+    for gs, ge in raw_gaps:
+        gap_mid = (gs + ge) / 2
+        gap_size = ge - gs
+        if gap_mid < header_zone_limit and gap_size > large_gap_threshold:
+            if gap_size > best_header_size:
+                best_header_size = gap_size
+                header_y = ge  # bottom edge of gap
+
+    best_footer_size = 0
+    for gs, ge in raw_gaps:
+        gap_mid = (gs + ge) / 2
+        gap_size = ge - gs
+        if gap_mid > footer_zone_start and gap_size > large_gap_threshold:
+            if gap_size > best_footer_size:
+                best_footer_size = gap_size
+                footer_y = gs  # top edge of gap
+
+    if header_y is not None:
+        logger.info(f"HeaderFooterGaps: header boundary at y={header_y} "
+                    f"(gap={best_header_size}px, median_gap={median_gap:.0f}px)")
+    if footer_y is not None:
+        logger.info(f"HeaderFooterGaps: footer boundary at y={footer_y} "
+                    f"(gap={best_footer_size}px, median_gap={median_gap:.0f}px)")
+
+    return header_y, footer_y
+
+
 def _add_header_footer(regions: List[PageRegion], top_y: int, bottom_y: int,
-                       img_w: int, img_h: int) -> None:
-    """Add header/footer regions in-place."""
-    if top_y > 10:
+                       img_w: int, img_h: int,
+                       inv: Optional[np.ndarray] = None) -> None:
+    """Add header/footer regions in-place.
+
+    When *inv* is provided, uses gap-based detection to find header/footer
+    boundaries. Falls back to simple top_y/bottom_y check otherwise.
+    """
+    header_y: Optional[int] = None
+    footer_y: Optional[int] = None
+
+    if inv is not None:
+        header_y, footer_y = _detect_header_footer_gaps(inv, img_w, img_h)
+
+    # Gap-based header
+    if header_y is not None and header_y > 10:
+        regions.append(PageRegion(type='header', x=0, y=0, width=img_w, height=header_y))
+    elif top_y > 10:
         regions.append(PageRegion(type='header', x=0, y=0, width=img_w, height=top_y))
-    if bottom_y < img_h - 10:
+
+    # Gap-based footer
+    if footer_y is not None and footer_y < img_h - 10:
+        regions.append(PageRegion(type='footer', x=0, y=footer_y, width=img_w, height=img_h - footer_y))
+    elif bottom_y < img_h - 10:
         regions.append(PageRegion(type='footer', x=0, y=bottom_y, width=img_w, height=img_h - bottom_y))
 
 
@@ -2576,7 +2685,7 @@ def analyze_layout_by_words(ocr_img: np.ndarray, dewarped_bgr: np.ndarray) -> Li
 
     # Phase B: Content-based classification
     regions = classify_column_types(geometries, content_w, top_y, w, h, bottom_y,
-                                    left_x=left_x, right_x=right_x)
+                                    left_x=left_x, right_x=right_x, inv=_inv)
 
     col_count = len([r for r in regions if r.type.startswith('column') or r.type == 'page_ref'])
     methods = set(r.classification_method for r in regions if r.classification_method)
diff --git a/klausur-service/backend/ocr_pipeline_api.py b/klausur-service/backend/ocr_pipeline_api.py
index 9da70a9..e70c168 100644
--- a/klausur-service/backend/ocr_pipeline_api.py
+++ b/klausur-service/backend/ocr_pipeline_api.py
@@ -700,7 +700,7 @@ async def detect_columns(session_id: str):
 
         # Phase B: Content-based classification
         regions = classify_column_types(geometries, content_w, top_y, w, h, bottom_y,
-                                        left_x=left_x, right_x=right_x)
+                                        left_x=left_x, right_x=right_x, inv=inv)
 
     duration = time.time() - t0
 
diff --git a/klausur-service/backend/tests/test_cv_vocab_pipeline.py b/klausur-service/backend/tests/test_cv_vocab_pipeline.py
index 0dd544d..6569df4 100644
--- a/klausur-service/backend/tests/test_cv_vocab_pipeline.py
+++ b/klausur-service/backend/tests/test_cv_vocab_pipeline.py
@@ -34,6 +34,7 @@ from cv_vocab_pipeline import (
     _find_content_bounds,
     _filter_narrow_runs,
     _build_margin_regions,
+    _detect_header_footer_gaps,
     analyze_layout,
     _group_words_into_lines,
     match_lines_to_vocab,
@@ -989,6 +990,106 @@ class TestMarginRegions:
             assert m.classification_method == 'content_bounds'
 
 
+# =============================================
+# Header/Footer Gap Detection
+# =============================================
+
+class TestHeaderFooterGapDetection:
+    """Tests for _detect_header_footer_gaps()."""
+
+    def _make_inv(self, height: int, width: int, bands: list) -> np.ndarray:
+        """Create an inverted binary image with white horizontal bands.
+
+        Args:
+            height: Image height.
+            width: Image width.
+            bands: List of (y_start, y_end) tuples where pixels are white (255).
+        """
+        inv = np.zeros((height, width), dtype=np.uint8)
+        for y1, y2 in bands:
+            inv[y1:y2, :] = 255
+        return inv
+
+    def _make_body_with_lines(self, h, w, body_start, body_end,
+                               line_h=15, gap_h=12):
+        """Create bands simulating text lines with inter-line gaps.
+
+        gap_h must be large enough to survive smoothing (kernel ~ h//200).
+        """
+        bands = []
+        y = body_start
+        while y + line_h <= body_end:
+            bands.append((y, y + line_h))
+            y += line_h + gap_h
+        return bands
+
+    def test_header_gap_detected(self):
+        """Content at top + large gap + main body → header_y at the gap."""
+        h, w = 2000, 800
+        # Header content at rows 20-80
+        bands = [(20, 80)]
+        # Large gap 80-300 (220px) — much larger than 12px line gaps
+        # Body lines from 300 to ~1990 (extends near bottom, no footer gap)
+        bands += self._make_body_with_lines(h, w, 300, 1990)
+        inv = self._make_inv(h, w, bands)
+        header_y, footer_y = _detect_header_footer_gaps(inv, w, h)
+        assert header_y is not None
+        assert 80 <= header_y <= 310
+
+    def test_footer_gap_detected(self):
+        """Main body + large gap + page number → footer_y at the gap."""
+        h, w = 2000, 800
+        # Body lines from 10 to 1600 (starts near top, no header gap)
+        bands = self._make_body_with_lines(h, w, 10, 1600)
+        # Large gap 1600-1880 (280px)
+        # Page number 1880-1920
+        bands.append((1880, 1920))
+        inv = self._make_inv(h, w, bands)
+        header_y, footer_y = _detect_header_footer_gaps(inv, w, h)
+        assert footer_y is not None
+        assert 1580 <= footer_y <= 1890
+
+    def test_both_header_and_footer(self):
+        """Header + gap + body lines + gap + footer → both detected."""
+        h, w = 2000, 800
+        # Header 10-60
+        bands = [(10, 60)]
+        # Large gap 60-250 (190px)
+        # Body lines from 250 to 1700
+        bands += self._make_body_with_lines(h, w, 250, 1700)
+        # Large gap 1700-1900 (200px)
+        # Footer 1900-1970
+        bands.append((1900, 1970))
+        inv = self._make_inv(h, w, bands)
+        header_y, footer_y = _detect_header_footer_gaps(inv, w, h)
+        assert header_y is not None
+        assert footer_y is not None
+        assert 60 <= header_y <= 260
+        assert 1690 <= footer_y <= 1910
+
+    def test_no_gaps_returns_none(self):
+        """Uniform content across the page → (None, None)."""
+        h, w = 1000, 800
+        # Content across entire height
+        inv = self._make_inv(h, w, [(0, 1000)])
+        header_y, footer_y = _detect_header_footer_gaps(inv, w, h)
+        assert header_y is None
+        assert footer_y is None
+
+    def test_small_gaps_ignored(self):
+        """Gaps smaller than 2x median should be ignored."""
+        h, w = 1000, 800
+        # Many small, evenly-spaced gaps (like line spacing) — no large outlier
+        bands = []
+        for row_start in range(0, 1000, 20):
+            bands.append((row_start, row_start + 15))  # 15px content, 5px gap
+        inv = self._make_inv(h, w, bands)
+        header_y, footer_y = _detect_header_footer_gaps(inv, w, h)
+        # All gaps are equal size, none > 2x median → no header/footer
+        assert header_y is None
+        assert footer_y is None
+
+
 # =============================================
 # RUN TESTS
 # =============================================