Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ocr-pipeline): add Step 5 word recognition (grid from columns × rows)

Browse Source 
Backend: build_word_grid() intersects column regions with content rows,
OCRs each cell with language-specific Tesseract, and returns vocabulary
entries with percent-based bounding boxes. New endpoints: POST /words,
GET /image/words-overlay, ground-truth save/retrieve for words.
Frontend: StepWordRecognition with overview + step-through labeling modes,
goToStep callback for row correction feedback loop.
MkDocs: OCR Pipeline documentation added.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-02-28 02:18:29 +01:00
parent 47dc2e6f7a
commit 954103cdf2
9 changed files with 1429 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
klausur-service/backend/ocr_pipeline_session_store.py
View File

@@ -80,7 +80,7 @@ async def create_session_db(
) VALUES ($1, $2, $3, $4, 'active', 1)
RETURNING id, name, filename, status, current_step,
deskew_result, dewarp_result, column_result, row_result,
ground_truth, auto_shear_degrees,
word_result, ground_truth, auto_shear_degrees,
created_at, updated_at
""", uuid.UUID(session_id), name, filename, original_png)
@@ -94,7 +94,7 @@ async def get_session_db(session_id: str) -> Optional[Dict[str, Any]]:
row = await conn.fetchrow("""
SELECT id, name, filename, status, current_step,
deskew_result, dewarp_result, column_result, row_result,
ground_truth, auto_shear_degrees,
word_result, ground_truth, auto_shear_degrees,
created_at, updated_at
FROM ocr_pipeline_sessions WHERE id = $1
""", uuid.UUID(session_id))
@@ -136,10 +136,10 @@ async def update_session_db(session_id: str, **kwargs) -> Optional[Dict[str, Any
'name', 'filename', 'status', 'current_step',
'original_png', 'deskewed_png', 'binarized_png', 'dewarped_png',
'deskew_result', 'dewarp_result', 'column_result', 'row_result',
'ground_truth', 'auto_shear_degrees',
'word_result', 'ground_truth', 'auto_shear_degrees',
}
jsonb_fields = {'deskew_result', 'dewarp_result', 'column_result', 'row_result', 'ground_truth'}
jsonb_fields = {'deskew_result', 'dewarp_result', 'column_result', 'row_result', 'word_result', 'ground_truth'}
for key, value in kwargs.items():
if key in allowed_fields:
@@ -164,7 +164,7 @@ async def update_session_db(session_id: str, **kwargs) -> Optional[Dict[str, Any
WHERE id = ${param_idx}
RETURNING id, name, filename, status, current_step,
deskew_result, dewarp_result, column_result, row_result,
ground_truth, auto_shear_degrees,
word_result, ground_truth, auto_shear_degrees,
created_at, updated_at
""", *values)
@@ -220,7 +220,7 @@ def _row_to_dict(row: asyncpg.Record) -> Dict[str, Any]:
result[key] = result[key].isoformat()
# JSONB → parsed (asyncpg returns str for JSONB)
for key in ['deskew_result', 'dewarp_result', 'column_result', 'row_result', 'ground_truth']:
for key in ['deskew_result', 'dewarp_result', 'column_result', 'row_result', 'word_result', 'ground_truth']:
if key in result and result[key] is not None:
if isinstance(result[key], str):
result[key] = json.loads(result[key])