49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
"""Image OCR endpoint."""
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException
|
|
|
|
from app.core.dependencies import get_image_processor, get_layout_detector, get_ocr_service
|
|
from app.schemas.image import ImageOCRRequest, ImageOCRResponse
|
|
from app.services.image_processor import ImageProcessor
|
|
from app.services.layout_detector import LayoutDetector
|
|
from app.services.ocr_service import OCRService
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
@router.post("/ocr", response_model=ImageOCRResponse)
|
|
async def process_image_ocr(
|
|
request: ImageOCRRequest,
|
|
image_processor: ImageProcessor = Depends(get_image_processor),
|
|
layout_detector: LayoutDetector = Depends(get_layout_detector),
|
|
ocr_service: OCRService = Depends(get_ocr_service),
|
|
) -> ImageOCRResponse:
|
|
"""Process an image and extract content as LaTeX, Markdown, and MathML.
|
|
|
|
The processing pipeline:
|
|
1. Load and preprocess image (add 30% whitespace padding)
|
|
2. Detect layout using DocLayout-YOLO
|
|
3. Based on layout:
|
|
- If plain text exists: use PP-DocLayoutV2 for mixed recognition
|
|
- Otherwise: use PaddleOCR-VL with formula prompt
|
|
4. Convert output to LaTeX, Markdown, and MathML formats
|
|
"""
|
|
|
|
image = image_processor.preprocess(
|
|
image_url=request.image_url,
|
|
image_base64=request.image_base64,
|
|
)
|
|
|
|
try:
|
|
# 3. Perform OCR based on layout
|
|
ocr_result = ocr_service.recognize(image)
|
|
except RuntimeError as e:
|
|
raise HTTPException(status_code=503, detail=str(e))
|
|
|
|
# 4. Return response
|
|
return ImageOCRResponse(
|
|
latex=ocr_result.get("latex", ""),
|
|
markdown=ocr_result.get("markdown", ""),
|
|
mathml=ocr_result.get("mathml", ""),
|
|
)
|