Struct OAROCR 

pub struct OAROCR { /* private fields */ }

OCR runtime for executing text detection and recognition.

This struct represents a configured OCR pipeline that can process images to extract text.

Implementations

impl OAROCR

pub fn predict( &self, images: Vec<RgbImage>, ) -> Result<Vec<OAROCRResult>, OCRError>

Predicts text from images using the configured OCR pipeline.

This method orchestrates the execution of all configured tasks in the pipeline, including optional components like document orientation, rectification, and text line orientation classification.

Arguments

• images - Collection of RGB images to process

Returns

A vector of OAROCRResult containing the OCR results for each image, or an error if processing fails.

Example

use oar_ocr::oarocr::ocr::OAROCRBuilder;
use oar_ocr::utils::load_image;
use std::path::Path;

let ocr = OAROCRBuilder::new(
    "models/det.onnx",
    "models/rec.onnx",
    "models/dict.txt",
).build()?;

let image = load_image(Path::new("document.jpg"))?;
let results = ocr.predict(vec![image])?;

for result in results {
    for region in result.text_regions {
        if let Some(text) = region.text {
            println!("Text: {}", text);
        }
    }
}

Trait Implementations

impl Debug for OAROCR

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.