Expand description
OCR fallback for scanned/image PDFs with no text layer — the bundled PP-OCRv6 pipeline, natively in
Rust. Two ONNX stages: DB detection (image → text-region probability map) and CRNN recognition
(each cropped region → text via CTC). Pages are rasterized with poppler pdftoppm. Gated behind the
ocr feature (implies docs/onnx).
Detection post-processing is a pragmatic axis-aligned variant: binarize the prob map, take connected components’ bounding boxes (documents are near-horizontal), unclip slightly, crop, recognize.
Structs§
Functions§
- ocr_pdf
- OCR a PDF by rasterizing its pages (poppler
pdftoppm, 150 dpi) and running the PP-OCRv6 pipeline. Returns concatenated page text, or None if rasterization/models are unavailable.