View Source Evision.Text.TextDetectorCNN (Evision v0.1.28)

Link to this section Summary

Types

t()

Type that represents an Text.TextDetectorCNN struct.

Link to this section Types

@type t() :: %Evision.Text.TextDetectorCNN{ref: reference()}

Type that represents an Text.TextDetectorCNN struct.

  • ref. reference()

    The underlying erlang resource variable.

Link to this section Functions

Link to this function

create(modelArchFilename, modelWeightsFilename)

View Source
@spec create(binary(), binary()) :: t() | {:error, String.t()}

create

Positional Arguments
Return
  • retval: TextDetectorCNN

Has overloading in C++

Python prototype (for reference only):

create(modelArchFilename, modelWeightsFilename) -> retval
Link to this function

detect(self, inputImage)

View Source
@spec detect(t(), Evision.Mat.maybe_mat_in()) ::
  {[{number(), number(), number(), number()}], [number()]}
  | {:error, String.t()}

detect

Positional Arguments
  • self: Evision.Text.TextDetectorCNN.t()

  • inputImage: Evision.Mat.t().

    an image expected to be a CV_U8C3 of any size

Return
  • bbox: [Rect].

    a vector of Rect that will store the detected word bounding box

  • confidence: [float].

    a vector of float that will be updated with the confidence the classifier has for the selected bounding box

Has overloading in C++

Python prototype (for reference only):

detect(inputImage) -> Bbox, confidence