egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: upgrade PP-StructureV3 models to latest versions

Browse Source 
- Layout: PP-DocLayout-S → PP-DocLayout_plus-L (83.2% mAP)
- Table: Single model → Dual SLANeXt (wired/wireless)
- Formula: PP-FormulaNet_plus-L for enhanced recognition
- Add preprocessing flags support (orientation, unwarping)
- Update frontend i18n descriptions

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-27 14:21:24 +08:00
parent 59206a6ab8
commit 6235280c45
9 changed files with 504 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
backend/app/core/config.py
View File

@@ -91,6 +91,11 @@ class Settings(BaseSettings):
enable_table_recognition: bool = Field(default=True) # Table structure recognition
enable_seal_recognition: bool = Field(default=True) # Seal/stamp recognition
enable_text_recognition: bool = Field(default=True) # General text recognition
# PP-StructureV3 Preprocessing (Stage 1)
use_doc_orientation_classify: bool = Field(default=True) # Auto-detect and correct document rotation
use_doc_unwarping: bool = Field(default=True) # Correct document warping from photos
use_textline_orientation: bool = Field(default=True) # Detect textline orientation
layout_detection_threshold: float = Field(default=0.2) # Lower threshold for more sensitive detection
layout_nms_threshold: float = Field(default=0.2) # Lower NMS to preserve more individual elements
layout_merge_mode: str = Field(default="small") # Use 'small' to minimize bbox merging
@@ -99,20 +104,48 @@ class Settings(BaseSettings):
text_det_box_thresh: float = Field(default=0.3) # Lower box threshold for better detection
text_det_unclip_ratio: float = Field(default=1.2) # Smaller unclip for tighter text boxes
# Layout Detection Model Configuration
# Layout Detection Model Configuration (Stage 3)
# Available models:
# - None (default): Use PP-StructureV3's built-in model (PubLayNet-based)
# - "PP-DocLayout-S": Better for Chinese docs, papers, contracts, exams (23 categories)
# - "PP-DocLayout_plus-L": Best for Chinese docs (83.2% mAP, 20 categories) - complex layouts
# - "PP-DocLayout-L": High accuracy (90.4% mAP, 23 categories) - general purpose
# - "picodet_lcnet_x1_0_fgd_layout_cdla": CDLA-based model for Chinese document layout
layout_detection_model_name: Optional[str] = Field(
default="PP-DocLayout-S",
description="Layout detection model name. Set to 'PP-DocLayout-S' for better Chinese document support."
default="PP-DocLayout_plus-L",
description="Layout detection model name. PP-DocLayout_plus-L recommended for complex Chinese documents."
)
layout_detection_model_dir: Optional[str] = Field(
default=None,
description="Custom layout detection model directory. If None, downloads official model."
)
# Table Structure Recognition Model Configuration (Stage 4)
# PP-StructureV3 uses separate models for wired (bordered) and wireless (borderless) tables
# Both models should be configured for comprehensive table detection
# Available models:
# - "SLANeXt_wired": Best for wired/bordered tables (69.65% accuracy, 351MB)
# - "SLANeXt_wireless": Best for wireless/borderless tables (69.65% accuracy, 351MB)
# - "SLANet": Legacy model (59.52% accuracy, 6.9MB)
# - "SLANet_plus": Improved legacy (63.69% accuracy, 6.9MB)
wired_table_model_name: Optional[str] = Field(
default="SLANeXt_wired",
description="Table structure model for bordered tables. SLANeXt_wired recommended."
)
wireless_table_model_name: Optional[str] = Field(
default="SLANeXt_wireless",
description="Table structure model for borderless tables. SLANeXt_wireless recommended."
)
# Formula Recognition Model Configuration (Stage 4)
# Available models:
# - "PP-FormulaNet_plus-L": Best for Chinese formulas (90.64% Chinese, 92.22% English BLEU)
# - "PP-FormulaNet-L": Good for English formulas (90.36% English BLEU)
# - "PP-FormulaNet-S": Fast inference (87% English BLEU)
formula_recognition_model_name: Optional[str] = Field(
default="PP-FormulaNet_plus-L",
description="Formula recognition model. PP-FormulaNet_plus-L recommended for Chinese formula support."
)
# ===== Gap Filling Configuration =====
# Supplements PP-StructureV3 output with raw OCR regions when detection is incomplete
gap_filling_enabled: bool = Field(default=True) # Enable gap filling for OCR track

8
backend/app/schemas/task.py
View File

@@ -28,11 +28,11 @@ class LayoutModelEnum(str, Enum):
"""Layout detection model selection for OCR track.
Different models are optimized for different document types:
- CHINESE: PP-DocLayout-S, optimized for Chinese documents (forms, contracts, invoices)
- DEFAULT: PubLayNet-based, optimized for English academic papers
- CDLA: CDLA model, specialized Chinese document layout analysis
- CHINESE: PP-DocLayout_plus-L (83.2% mAP), optimized for complex Chinese documents
- DEFAULT: PubLayNet-based (~94% mAP), optimized for English academic papers
- CDLA: CDLA model (~86% mAP), specialized Chinese document layout analysis
"""
CHINESE = "chinese" # PP-DocLayout-S - Best for Chinese documents (recommended)
CHINESE = "chinese" # PP-DocLayout_plus-L - Best for Chinese documents (recommended)
DEFAULT = "default" # PubLayNet-based - Best for English documents
CDLA = "cdla" # CDLA model - Alternative for Chinese layout

56
backend/app/services/ocr_service.py
View File

@@ -50,11 +50,11 @@ logger = logging.getLogger(__name__)
_USE_PUBLAYNET_DEFAULT = "__USE_PUBLAYNET_DEFAULT__"
# Layout model mapping: user-friendly names to actual model names
# - "chinese": PP-DocLayout-S - Best for Chinese documents (forms, contracts, invoices)
# - "chinese": PP-DocLayout_plus-L - Best for Chinese documents (83.2% mAP, complex layouts)
# - "default": PubLayNet-based default model - Best for English documents
# - "cdla": picodet_lcnet_x1_0_fgd_layout_cdla - Alternative for Chinese layout
LAYOUT_MODEL_MAPPING = {
"chinese": "PP-DocLayout-S",
"chinese": "PP-DocLayout_plus-L",
"default": _USE_PUBLAYNET_DEFAULT, # Uses default PubLayNet-based model (no custom model)
"cdla": "picodet_lcnet_x1_0_fgd_layout_cdla",
}
@@ -517,34 +517,63 @@ class OCRService:
layout_model_name = settings.layout_detection_model_name
layout_model_dir = settings.layout_detection_model_dir
# Preprocessing configuration (Stage 1)
use_orientation = settings.use_doc_orientation_classify
use_unwarping = settings.use_doc_unwarping
use_textline = settings.use_textline_orientation
# Table and formula model configuration (Stage 4)
wired_table_model = settings.wired_table_model_name
wireless_table_model = settings.wireless_table_model_name
formula_model = settings.formula_recognition_model_name
logger.info(f"PP-StructureV3 config: table={use_table}, formula={use_formula}, chart={use_chart}")
logger.info(f"Preprocessing: orientation={use_orientation}, unwarping={use_unwarping}, textline={use_textline}")
logger.info(f"Layout model: name={layout_model_name}, dir={layout_model_dir}")
logger.info(f"Table models: wired={wired_table_model}, wireless={wireless_table_model}")
logger.info(f"Formula model: {formula_model}")
logger.info(f"Layout config: threshold={layout_threshold}, nms={layout_nms}, merge={layout_merge}, unclip={layout_unclip}")
logger.info(f"Text detection: thresh={text_thresh}, box_thresh={text_box_thresh}, unclip={text_unclip}")
# Build PPStructureV3 kwargs
pp_kwargs = {
'use_doc_orientation_classify': False,
'use_doc_unwarping': False,
'use_textline_orientation': False,
# Preprocessing (Stage 1)
'use_doc_orientation_classify': use_orientation,
'use_doc_unwarping': use_unwarping,
'use_textline_orientation': use_textline,
# Element recognition (Stage 4)
'use_table_recognition': use_table,
'use_formula_recognition': use_formula,
'use_chart_recognition': use_chart,
# Layout detection parameters
'layout_threshold': layout_threshold,
'layout_nms': layout_nms,
'layout_unclip_ratio': layout_unclip,
'layout_merge_bboxes_mode': layout_merge,
# Text detection parameters
'text_det_thresh': text_thresh,
'text_det_box_thresh': text_box_thresh,
'text_det_unclip_ratio': text_unclip,
}
# Add layout model configuration if specified
# Add layout model configuration if specified (Stage 3)
if layout_model_name:
pp_kwargs['layout_detection_model_name'] = layout_model_name
if layout_model_dir:
pp_kwargs['layout_detection_model_dir'] = layout_model_dir
# Add table structure model configuration (Stage 4)
# PPStructureV3 uses separate models for wired (bordered) and wireless (borderless) tables
# Both models should be configured for comprehensive table detection
if wired_table_model:
pp_kwargs['wired_table_structure_recognition_model_name'] = wired_table_model
if wireless_table_model:
pp_kwargs['wireless_table_structure_recognition_model_name'] = wireless_table_model
# Add formula recognition model configuration (Stage 4)
if formula_model:
pp_kwargs['formula_recognition_model_name'] = formula_model
self.structure_engine = PPStructureV3(**pp_kwargs)
# Track model loading for cache management
@@ -571,12 +600,15 @@ class OCRService:
layout_threshold = settings.layout_detection_threshold
layout_model_name = settings.layout_detection_model_name
layout_model_dir = settings.layout_detection_model_dir
wired_table_model = settings.wired_table_model_name
wireless_table_model = settings.wireless_table_model_name
formula_model = settings.formula_recognition_model_name
# Build CPU fallback kwargs
cpu_kwargs = {
'use_doc_orientation_classify': False,
'use_doc_unwarping': False,
'use_textline_orientation': False,
'use_doc_orientation_classify': settings.use_doc_orientation_classify,
'use_doc_unwarping': settings.use_doc_unwarping,
'use_textline_orientation': settings.use_textline_orientation,
'use_table_recognition': use_table,
'use_formula_recognition': use_formula,
'use_chart_recognition': use_chart,
@@ -586,6 +618,12 @@ class OCRService:
cpu_kwargs['layout_detection_model_name'] = layout_model_name
if layout_model_dir:
cpu_kwargs['layout_detection_model_dir'] = layout_model_dir
if wired_table_model:
cpu_kwargs['wired_table_structure_recognition_model_name'] = wired_table_model
if wireless_table_model:
cpu_kwargs['wireless_table_structure_recognition_model_name'] = wireless_table_model
if formula_model:
cpu_kwargs['formula_recognition_model_name'] = formula_model
self.structure_engine = PPStructureV3(**cpu_kwargs)
self._current_layout_model = layout_model # Track current model for recreation check

10
backend/tests/services/test_layout_model.py
View File

@@ -40,8 +40,8 @@ class TestLayoutModelMapping:
assert 'cdla' in LAYOUT_MODEL_MAPPING
def test_chinese_model_maps_to_pp_doclayout(self):
"""Verify 'chinese' maps to PP-DocLayout-S"""
assert LAYOUT_MODEL_MAPPING['chinese'] == 'PP-DocLayout-S'
"""Verify 'chinese' maps to PP-DocLayout_plus-L"""
assert LAYOUT_MODEL_MAPPING['chinese'] == 'PP-DocLayout_plus-L'
def test_default_model_maps_to_publaynet_sentinel(self):
"""Verify 'default' maps to sentinel value for PubLayNet default"""
@@ -57,7 +57,7 @@ class TestLayoutModelEngine:
"""Test engine creation with different layout models"""
def test_chinese_model_creates_engine_with_pp_doclayout(self):
"""Verify 'chinese' layout model uses PP-DocLayout-S"""
"""Verify 'chinese' layout model uses PP-DocLayout_plus-L"""
ocr_service = OCRService()
with patch.object(ocr_service, 'structure_engine', None):
@@ -70,7 +70,7 @@ class TestLayoutModelEngine:
mock_ppstructure.assert_called_once()
call_kwargs = mock_ppstructure.call_args[1]
assert call_kwargs.get('layout_detection_model_name') == 'PP-DocLayout-S'
assert call_kwargs.get('layout_detection_model_name') == 'PP-DocLayout_plus-L'
def test_default_model_creates_engine_without_model_name(self):
"""Verify 'default' layout model does not specify model name (uses default)"""
@@ -121,7 +121,7 @@ class TestLayoutModelEngine:
call_kwargs = mock_ppstructure.call_args[1]
# Should use 'chinese' model as default
assert call_kwargs.get('layout_detection_model_name') == 'PP-DocLayout-S'
assert call_kwargs.get('layout_detection_model_name') == 'PP-DocLayout_plus-L'
class TestLayoutModelCaching: