Trait opencv::prelude::TextDetectorCNN

pub trait TextDetectorCNN: TextDetector + TextDetectorCNNConst {
    fn as_raw_mut_TextDetectorCNN(&mut self) -> *mut c_void;

    fn detect(
        &mut self,
        input_image: &dyn ToInputArray,
        bbox: &mut Vector<Rect>,
        confidence: &mut Vector<f32>
    ) -> Result<()> { ... }
}

Required Methods

fn as_raw_mut_TextDetectorCNN(&mut self) -> *mut c_void

Provided Methods

fn detect(
    &mut self,
    input_image: &dyn ToInputArray,
    bbox: &mut Vector<Rect>,
    confidence: &mut Vector<f32>
) -> Result<()>

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

• inputImage: an image expected to be a CV_U8C3 of any size
• Bbox: a vector of Rect that will store the detected word bounding box
• confidence: a vector of float that will be updated with the confidence the classifier has for the selected bounding box

Implementations

impl dyn TextDetectorCNN + '_

pub fn create_with_sizes(
    model_arch_filename: &str,
    model_weights_filename: &str,
    detection_sizes: Vector<Size>
) -> Result<Ptr<dyn TextDetectorCNN>>

Creates an instance of the TextDetectorCNN class using the provided parameters.

Parameters

• modelArchFilename: the relative or absolute path to the prototxt file describing the classifiers architecture.
• modelWeightsFilename: the relative or absolute path to the file containing the pretrained weights of the model in caffe-binary form.
• detectionSizes: a list of sizes for multiscale detection. The values[(300,300),(700,500),(700,300),(700,700),(1600,1600)] are recommended in LiaoSBWL17 to achieve the best quality.

pub fn create(
    model_arch_filename: &str,
    model_weights_filename: &str
) -> Result<Ptr<dyn TextDetectorCNN>>

Creates an instance of the TextDetectorCNN class using the provided parameters.

Parameters

• modelArchFilename: the relative or absolute path to the prototxt file describing the classifiers architecture.
• modelWeightsFilename: the relative or absolute path to the file containing the pretrained weights of the model in caffe-binary form.
• detectionSizes: a list of sizes for multiscale detection. The values[(300,300),(700,500),(700,300),(700,700),(1600,1600)] are recommended in LiaoSBWL17 to achieve the best quality.

Overloaded parameters

Implementors

impl TextDetectorCNN for PtrOfTextDetectorCNN