Trait opencv::dnn::prelude::TextDetectionModelTraitConst

source · 
pub trait TextDetectionModelTraitConst: ModelTraitConst {
    // Required method
    fn as_raw_TextDetectionModel(&self) -> *const c_void;

    // Provided methods
    fn detect_with_confidences(
        &self,
        frame: &impl ToInputArray,
        detections: &mut Vector<Vector<Point>>,
        confidences: &mut Vector<f32>
    ) -> Result<()> { ... }
    fn detect(
        &self,
        frame: &impl ToInputArray,
        detections: &mut Vector<Vector<Point>>
    ) -> Result<()> { ... }
    fn detect_text_rectangles(
        &self,
        frame: &impl ToInputArray,
        detections: &mut Vector<RotatedRect>,
        confidences: &mut Vector<f32>
    ) -> Result<()> { ... }
    fn detect_text_rectangles_1(
        &self,
        frame: &impl ToInputArray,
        detections: &mut Vector<RotatedRect>
    ) -> Result<()> { ... }
}
Expand description

Constant methods for crate::dnn::TextDetectionModel

Required Methods§

source

fn as_raw_TextDetectionModel(&self) -> *const c_void

Provided Methods§

source

fn detect_with_confidences( &self, frame: &impl ToInputArray, detections: &mut Vector<Vector<Point>>, confidences: &mut Vector<f32> ) -> Result<()>

Performs detection

Given the input @p frame, prepare network input, run network inference, post-process network output and return result detections.

Each result is quadrangle’s 4 points in this order:

  • bottom-left
  • top-left
  • top-right
  • bottom-right

Use cv::getPerspectiveTransform function to retrieve image region without perspective transformations.

Note: If DL model doesn’t support that kind of output then result may be derived from detectTextRectangles() output.

Parameters
  • frame: The input image
  • detections:[out] array with detections’ quadrangles (4 points per result)
  • confidences:[out] array with detection confidences
source

fn detect( &self, frame: &impl ToInputArray, detections: &mut Vector<Vector<Point>> ) -> Result<()>

Performs detection

Given the input @p frame, prepare network input, run network inference, post-process network output and return result detections.

Each result is quadrangle’s 4 points in this order:

  • bottom-left
  • top-left
  • top-right
  • bottom-right

Use cv::getPerspectiveTransform function to retrieve image region without perspective transformations.

Note: If DL model doesn’t support that kind of output then result may be derived from detectTextRectangles() output.

Parameters
  • frame: The input image
  • detections:[out] array with detections’ quadrangles (4 points per result)
  • confidences:[out] array with detection confidences
Overloaded parameters
source

fn detect_text_rectangles( &self, frame: &impl ToInputArray, detections: &mut Vector<RotatedRect>, confidences: &mut Vector<f32> ) -> Result<()>

Performs detection

Given the input @p frame, prepare network input, run network inference, post-process network output and return result detections.

Each result is rotated rectangle.

Note: Result may be inaccurate in case of strong perspective transformations.

Parameters
  • frame: the input image
  • detections:[out] array with detections’ RotationRect results
  • confidences:[out] array with detection confidences
source

fn detect_text_rectangles_1( &self, frame: &impl ToInputArray, detections: &mut Vector<RotatedRect> ) -> Result<()>

Performs detection

Given the input @p frame, prepare network input, run network inference, post-process network output and return result detections.

Each result is rotated rectangle.

Note: Result may be inaccurate in case of strong perspective transformations.

Parameters
  • frame: the input image
  • detections:[out] array with detections’ RotationRect results
  • confidences:[out] array with detection confidences
Overloaded parameters

Object Safety§

This trait is not object safe.

Implementors§