Struct leptess::LepTess

pub struct LepTess { /* fields omitted */ }

High level wrapper for Tesseract and Leptonica

Examples

Full page OCR

let mut lt = leptess::LepTess::new(Some("./tests/tessdata"), "eng").unwrap();
lt.set_image("./tests/di.png");
println!("{}", lt.get_utf8_text().unwrap());

OCR on a specific region of the image

lt.set_rectangle(&leptess::leptonica::Box::new(
    10, 10, 200, 60,
).unwrap());
println!("{}", lt.get_utf8_text().unwrap());

Iterate bounding boxes for each recognized word

let boxes = lt.get_component_boxes(
    leptess::capi::TessPageIteratorLevel_RIL_WORD,
    true,
).unwrap();

for b in &boxes {
    println!("{:?}", b.get_val());
}

Methods

impl LepTess

pub fn new(
    data_path: Option<&str>,
    lang: &str
) -> Result<LepTess, TessInitError>

pub fn set_image(&mut self, img_uri: &str) -> bool

Set image to use for OCR.

pub fn recognize(&self) -> i32

pub fn set_rectangle<'a, 'b>(&'a mut self, b: &'b Box)

Restrict OCR to a specific region of the image.

pub fn get_utf8_text(&self) -> Result<String, Utf8Error>

Extract text from current selected region of the image. By default, it is the full page. But it can be changed through set_rectangle api.

Example

let mut lt = leptess::LepTess::new(None, "eng").unwrap();
lt.set_image("./tests/di.png");
println!("{}", lt.get_utf8_text().unwrap());

pub fn mean_text_conf(&self) -> i32

pub fn get_regions(&self) -> Option<Boxa>

pub fn get_component_boxes(
    &self,
    level: TessPageIteratorLevel,
    text_only: bool
) -> Option<Boxa>

Get the given level kind of components (block, textline, word etc.) as a leptonica-style Boxa, in reading order.If text_only is true, then only text components are returned.

Example

Get word bounding boxes

let mut lt = leptess::LepTess::new(None, "eng").unwrap();
lt.set_image("./tests/di.png");
let boxes = lt.get_component_boxes(
    leptess::capi::TessPageIteratorLevel_RIL_WORD,
    true,
).unwrap();

for b in &boxes {
    println!("{:?}", b.get_val());
}