Document OCR pipeline in pure Rust: scanned PDF / multi-page TIFF / image → Markdown. PaddleOCR PP-OCRv6 and Tesseract 5.5 as interchangeable engines, PP-DocLayoutV3 layout for both.
usestd::path::Path;useimage::RgbImage;usecrate::error::Result;/// Carica una singola immagine (PNG, JPEG, BMP, TIFF pagina singola, …)
/// e la converte in RGB8.
pubfnload_image(path: impl AsRef<Path>)->Result<RgbImage>{Ok(image::open(path)?.to_rgb8())}