Struct cv::objdetect::CascadeClassifier

pub struct CascadeClassifier { /* fields omitted */ }

Cascade classifier class for object detection.

Implementations

impl CascadeClassifier

pub fn new() -> CascadeClassifier

Creates a cascade classifier, uninitialized. Before use, call load.

pub fn from_path<P: AsRef<Path>>(path: P) -> Result<Self, Error>

Creates a cascade classifier using the model specified.

pub fn load<P: AsRef<Path>>(&self, path: P) -> Result<(), Error>

Loads the classifier model from a path.

pub fn detect_multiscale(&self, mat: &Mat) -> Vec<Rect>

The default detection uses scale factor 1.1, minNeighbors 3, no min size or max size.

pub fn detect_with_params(
    &self,
    mat: &Mat,
    scale_factor: f32,
    min_neighbors: c_int,
    min_size: Size2i,
    max_size: Size2i
) -> Vec<Rect>

Detects the object using parameters specified.

• mat - Matrix of the type CV_8U containing an image where objects are detected.
• scale_factor - Parameter specifying how much the image size is reduced at each image scale.
• min_neighbors - Parameter specifying how many neighbors each candidate rectangle should have to retain it.
• min_size - Minimum possible object size. Objects smaller than that are ignored.
• max_size - Maximum possible object size. Objects larger than that are ignored

OpenCV has a parameter (flags) that’s not used at all.

Trait Implementations

impl Debug for CascadeClassifier

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

Formats the value using the given formatter.

impl Drop for CascadeClassifier

fn drop(&mut self)

Executes the destructor for this type.

impl ObjectDetect for CascadeClassifier

fn detect(&self, image: &Mat) -> Vec<(Rect, f64)>

Detects the object inside this image and returns a list of detections with their confidence.

impl Send for CascadeClassifier

We can safely send the classifier (a mutable pointer) to a different thread