feat(ocr-pipeline): distinguish header/footer vs margin_top/margin_bottom
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 29s
CI / test-go-edu-search (push) Successful in 27s
CI / test-python-klausur (push) Failing after 2m0s
CI / test-python-agent-core (push) Successful in 18s
CI / test-nodejs-website (push) Successful in 19s

Check for actual ink content in detected top/bottom regions:
- 'header'/'footer' when text is present (e.g. title, page number)
- 'margin_top'/'margin_bottom' when the region is empty page margin

Also update all skip-type sets and color maps for the new types.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-02 16:55:41 +01:00
parent f615c5f66d
commit c8981423d4
3 changed files with 134 additions and 27 deletions

View File

@@ -98,7 +98,7 @@ ENGLISH_FUNCTION_WORDS = {'the', 'a', 'an', 'is', 'are', 'was', 'were', 'to', 'o
@dataclass @dataclass
class PageRegion: class PageRegion:
"""A detected region on the page.""" """A detected region on the page."""
type: str # 'column_en', 'column_de', 'column_example', 'page_ref', 'column_marker', 'column_text', 'header', 'footer' type: str # 'column_en', 'column_de', 'column_example', 'page_ref', 'column_marker', 'column_text', 'header', 'footer', 'margin_top', 'margin_bottom'
x: int x: int
y: int y: int
width: int width: int
@@ -924,12 +924,10 @@ def analyze_layout(layout_img: np.ndarray, ocr_img: np.ndarray) -> List[PageRegi
# Add header/footer info (gap-based detection with fallback) # Add header/footer info (gap-based detection with fallback)
_add_header_footer(regions, top_y, bottom_y, w, h, inv=inv) _add_header_footer(regions, top_y, bottom_y, w, h, inv=inv)
has_header = any(r.type == 'header' for r in regions) top_region = next((r.type for r in regions if r.type in ('header', 'margin_top')), 'none')
has_footer = any(r.type == 'footer' for r in regions) bottom_region = next((r.type for r in regions if r.type in ('footer', 'margin_bottom')), 'none')
col_count = len([r for r in regions if r.type.startswith('column')]) col_count = len([r for r in regions if r.type.startswith('column')])
logger.info(f"Layout: {col_count} columns, " logger.info(f"Layout: {col_count} columns, top={top_region}, bottom={bottom_region}")
f"header={'yes' if has_header else 'no'}, "
f"footer={'yes' if has_footer else 'no'}")
return regions return regions
@@ -2042,7 +2040,8 @@ def _build_margin_regions(
# Right margin: from end of last content column to image edge # Right margin: from end of last content column to image edge
non_margin = [r for r in all_regions non_margin = [r for r in all_regions
if r.type not in ('margin_left', 'margin_right', 'header', 'footer')] if r.type not in ('margin_left', 'margin_right', 'header', 'footer',
'margin_top', 'margin_bottom')]
if non_margin: if non_margin:
last_col_end = max(r.x + r.width for r in non_margin) last_col_end = max(r.x + r.width for r in non_margin)
else: else:
@@ -2625,13 +2624,37 @@ def _detect_header_footer_gaps(
return header_y, footer_y return header_y, footer_y
def _region_has_content(inv: np.ndarray, y_start: int, y_end: int,
min_density: float = 0.005) -> bool:
"""Check whether a horizontal strip contains meaningful ink.
Args:
inv: Inverted binarized image (white-on-black).
y_start: Top of the region (inclusive).
y_end: Bottom of the region (exclusive).
min_density: Fraction of white pixels required to count as content.
Returns:
True if the region contains text/graphics, False if empty margin.
"""
if y_start >= y_end:
return False
strip = inv[y_start:y_end, :]
density = float(np.sum(strip)) / (strip.shape[0] * strip.shape[1] * 255)
return density > min_density
def _add_header_footer(regions: List[PageRegion], top_y: int, bottom_y: int, def _add_header_footer(regions: List[PageRegion], top_y: int, bottom_y: int,
img_w: int, img_h: int, img_w: int, img_h: int,
inv: Optional[np.ndarray] = None) -> None: inv: Optional[np.ndarray] = None) -> None:
"""Add header/footer regions in-place. """Add header/footer/margin regions in-place.
When *inv* is provided, uses gap-based detection to find header/footer Uses gap-based detection when *inv* is provided, otherwise falls back
boundaries. Falls back to simple top_y/bottom_y check otherwise. to simple top_y/bottom_y bounds.
Region types depend on whether there is actual content (text/graphics):
- 'header' / 'footer' — region contains text (e.g. title, page number)
- 'margin_top' / 'margin_bottom' — region is empty page margin
""" """
header_y: Optional[int] = None header_y: Optional[int] = None
footer_y: Optional[int] = None footer_y: Optional[int] = None
@@ -2639,17 +2662,28 @@ def _add_header_footer(regions: List[PageRegion], top_y: int, bottom_y: int,
if inv is not None: if inv is not None:
header_y, footer_y = _detect_header_footer_gaps(inv, img_w, img_h) header_y, footer_y = _detect_header_footer_gaps(inv, img_w, img_h)
# Gap-based header # --- Top region ---
if header_y is not None and header_y > 10: top_boundary = header_y if header_y is not None and header_y > 10 else (
regions.append(PageRegion(type='header', x=0, y=0, width=img_w, height=header_y)) top_y if top_y > 10 else None
elif top_y > 10: )
regions.append(PageRegion(type='header', x=0, y=0, width=img_w, height=top_y)) if top_boundary is not None:
has_content = inv is not None and _region_has_content(inv, 0, top_boundary)
rtype = 'header' if has_content else 'margin_top'
regions.append(PageRegion(type=rtype, x=0, y=0, width=img_w, height=top_boundary))
logger.info(f"HeaderFooter: top region type={rtype} height={top_boundary}px "
f"(has_content={has_content})")
# Gap-based footer # --- Bottom region ---
if footer_y is not None and footer_y < img_h - 10: bottom_boundary = footer_y if footer_y is not None and footer_y < img_h - 10 else (
regions.append(PageRegion(type='footer', x=0, y=footer_y, width=img_w, height=img_h - footer_y)) bottom_y if bottom_y < img_h - 10 else None
elif bottom_y < img_h - 10: )
regions.append(PageRegion(type='footer', x=0, y=bottom_y, width=img_w, height=img_h - bottom_y)) if bottom_boundary is not None:
has_content = inv is not None and _region_has_content(inv, bottom_boundary, img_h)
rtype = 'footer' if has_content else 'margin_bottom'
regions.append(PageRegion(type=rtype, x=0, y=bottom_boundary, width=img_w,
height=img_h - bottom_boundary))
logger.info(f"HeaderFooter: bottom region type={rtype} y={bottom_boundary} "
f"height={img_h - bottom_boundary}px (has_content={has_content})")
# --- Main Entry Point --- # --- Main Entry Point ---
@@ -2690,7 +2724,7 @@ def analyze_layout_by_words(ocr_img: np.ndarray, dewarped_bgr: np.ndarray) -> Li
col_count = len([r for r in regions if r.type.startswith('column') or r.type == 'page_ref']) 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) methods = set(r.classification_method for r in regions if r.classification_method)
logger.info(f"LayoutByWords: {col_count} columns detected (methods: {methods}): " logger.info(f"LayoutByWords: {col_count} columns detected (methods: {methods}): "
f"{[(r.type, r.x, r.width, r.classification_confidence) for r in regions if r.type not in ('header','footer')]}") f"{[(r.type, r.x, r.width, r.classification_confidence) for r in regions if r.type not in ('header','footer','margin_top','margin_bottom')]}")
return regions return regions
@@ -3797,7 +3831,7 @@ def build_cell_grid(
return [], [] return [], []
# Use columns only — skip ignore, header, footer, page_ref # Use columns only — skip ignore, header, footer, page_ref
_skip_types = {'column_ignore', 'header', 'footer', 'page_ref', 'margin_left', 'margin_right'} _skip_types = {'column_ignore', 'header', 'footer', 'margin_top', 'margin_bottom', 'page_ref', 'margin_left', 'margin_right'}
relevant_cols = [c for c in column_regions if c.type not in _skip_types] relevant_cols = [c for c in column_regions if c.type not in _skip_types]
if not relevant_cols: if not relevant_cols:
logger.warning("build_cell_grid: no usable columns found") logger.warning("build_cell_grid: no usable columns found")
@@ -3959,7 +3993,7 @@ def build_cell_grid_streaming(
if not content_rows: if not content_rows:
return return
_skip_types = {'column_ignore', 'header', 'footer', 'page_ref', 'margin_left', 'margin_right'} _skip_types = {'column_ignore', 'header', 'footer', 'margin_top', 'margin_bottom', 'page_ref', 'margin_left', 'margin_right'}
relevant_cols = [c for c in column_regions if c.type not in _skip_types] relevant_cols = [c for c in column_regions if c.type not in _skip_types]
if not relevant_cols: if not relevant_cols:
return return
@@ -4444,7 +4478,7 @@ def run_multi_pass_ocr(ocr_img: np.ndarray,
""" """
results: Dict[str, List[Dict]] = {} results: Dict[str, List[Dict]] = {}
_ocr_skip = {'header', 'footer', 'margin_left', 'margin_right'} _ocr_skip = {'header', 'footer', 'margin_top', 'margin_bottom', 'margin_left', 'margin_right'}
for region in regions: for region in regions:
if region.type in _ocr_skip: if region.type in _ocr_skip:
continue # Skip non-content regions continue # Skip non-content regions

View File

@@ -840,6 +840,8 @@ async def _get_columns_overlay(session_id: str) -> Response:
"column_ignore": (180, 180, 180), # Light Gray "column_ignore": (180, 180, 180), # Light Gray
"header": (128, 128, 128), # Gray "header": (128, 128, 128), # Gray
"footer": (128, 128, 128), # Gray "footer": (128, 128, 128), # Gray
"margin_top": (100, 100, 100), # Dark Gray
"margin_bottom": (100, 100, 100), # Dark Gray
} }
overlay = img.copy() overlay = img.copy()
@@ -1226,7 +1228,7 @@ async def _word_stream_generator(
# Compute grid shape upfront for the meta event # Compute grid shape upfront for the meta event
n_content_rows = len([r for r in row_geoms if r.row_type == 'content']) n_content_rows = len([r for r in row_geoms if r.row_type == 'content'])
_skip_types = {'column_ignore', 'header', 'footer', 'page_ref'} _skip_types = {'column_ignore', 'header', 'footer', 'margin_top', 'margin_bottom', 'page_ref'}
n_cols = len([c for c in col_regions if c.type not in _skip_types]) n_cols = len([c for c in col_regions if c.type not in _skip_types])
# Determine layout # Determine layout
@@ -1712,6 +1714,8 @@ async def _get_rows_overlay(session_id: str) -> Response:
"content": (255, 180, 0), # Blue "content": (255, 180, 0), # Blue
"header": (128, 128, 128), # Gray "header": (128, 128, 128), # Gray
"footer": (128, 128, 128), # Gray "footer": (128, 128, 128), # Gray
"margin_top": (100, 100, 100), # Dark Gray
"margin_bottom": (100, 100, 100), # Dark Gray
} }
overlay = img.copy() overlay = img.copy()

View File

@@ -35,6 +35,8 @@ from cv_vocab_pipeline import (
_filter_narrow_runs, _filter_narrow_runs,
_build_margin_regions, _build_margin_regions,
_detect_header_footer_gaps, _detect_header_footer_gaps,
_region_has_content,
_add_header_footer,
analyze_layout, analyze_layout,
_group_words_into_lines, _group_words_into_lines,
match_lines_to_vocab, match_lines_to_vocab,
@@ -340,7 +342,8 @@ class TestLayoutAnalysis:
ocr_img = create_ocr_image(text_like_image) ocr_img = create_ocr_image(text_like_image)
layout_img = create_layout_image(text_like_image) layout_img = create_layout_image(text_like_image)
regions = analyze_layout(layout_img, ocr_img) regions = analyze_layout(layout_img, ocr_img)
valid_types = {'column_en', 'column_de', 'column_example', 'header', 'footer'} valid_types = {'column_en', 'column_de', 'column_example',
'header', 'footer', 'margin_top', 'margin_bottom'}
for r in regions: for r in regions:
assert r.type in valid_types, f"Unexpected region type: {r.type}" assert r.type in valid_types, f"Unexpected region type: {r.type}"
@@ -976,7 +979,7 @@ class TestMarginRegions:
def test_margins_in_skip_types(self): def test_margins_in_skip_types(self):
"""Verify margin types are in the skip set used by build_cell_grid.""" """Verify margin types are in the skip set used by build_cell_grid."""
skip = {'column_ignore', 'header', 'footer', 'page_ref', 'margin_left', 'margin_right'} skip = {'column_ignore', 'header', 'footer', 'margin_top', 'margin_bottom', 'page_ref', 'margin_left', 'margin_right'}
assert 'margin_left' in skip assert 'margin_left' in skip
assert 'margin_right' in skip assert 'margin_right' in skip
@@ -1090,6 +1093,72 @@ class TestHeaderFooterGapDetection:
assert footer_y is None assert footer_y is None
class TestRegionContentCheck:
"""Tests for _region_has_content() and _add_header_footer() type selection."""
def _make_inv(self, height: int, width: int, bands: list) -> np.ndarray:
inv = np.zeros((height, width), dtype=np.uint8)
for y1, y2 in bands:
inv[y1:y2, :] = 255
return inv
def test_region_with_text_has_content(self):
"""Strip with ink → True."""
inv = self._make_inv(1000, 800, [(10, 50)])
assert _region_has_content(inv, 0, 100) is True
def test_empty_region_no_content(self):
"""Strip without ink → False."""
inv = self._make_inv(1000, 800, [(500, 600)])
assert _region_has_content(inv, 0, 100) is False
def test_header_with_text_is_header(self):
"""Top region with text → type='header' (via content bounds fallback)."""
h, w = 1000, 800
# Header text at 20-60, body starts at 200
inv = self._make_inv(h, w, [(20, 60), (200, 900)])
regions: list = []
# Simulate content bounds detecting body start at y=200
_add_header_footer(regions, top_y=200, bottom_y=h, img_w=w, img_h=h, inv=inv)
top_regions = [r for r in regions if r.type in ('header', 'margin_top')]
assert len(top_regions) == 1
assert top_regions[0].type == 'header' # text at 20-60 → header
def test_empty_top_is_margin_top(self):
"""Top region without text → type='margin_top'."""
h, w = 1000, 800
# Content only in body area (200-900), nothing in top 200px
inv = self._make_inv(h, w, [(200, 900)])
regions: list = []
# Simulate top_y=200 from content bounds
_add_header_footer(regions, top_y=200, bottom_y=h, img_w=w, img_h=h, inv=inv)
top_regions = [r for r in regions if r.type in ('header', 'margin_top')]
assert len(top_regions) == 1
assert top_regions[0].type == 'margin_top'
def test_empty_bottom_is_margin_bottom(self):
"""Bottom region without text → type='margin_bottom'."""
h, w = 1000, 800
# Content only in top/body (50-700), nothing below 700
inv = self._make_inv(h, w, [(50, 700)])
regions: list = []
_add_header_footer(regions, top_y=50, bottom_y=700, img_w=w, img_h=h, inv=inv)
bottom_regions = [r for r in regions if r.type in ('footer', 'margin_bottom')]
assert len(bottom_regions) == 1
assert bottom_regions[0].type == 'margin_bottom'
def test_footer_with_page_number_is_footer(self):
"""Bottom region with page number text → type='footer'."""
h, w = 1000, 800
# Body 50-700, page number at 900-930
inv = self._make_inv(h, w, [(50, 700), (900, 930)])
regions: list = []
_add_header_footer(regions, top_y=50, bottom_y=700, img_w=w, img_h=h, inv=inv)
bottom_regions = [r for r in regions if r.type in ('footer', 'margin_bottom')]
assert len(bottom_regions) == 1
assert bottom_regions[0].type == 'footer'
# ============================================= # =============================================
# RUN TESTS # RUN TESTS
# ============================================= # =============================================