View Source Evision.FaceRecognizerSF (Evision v0.1.9)

Link to this section Summary

cv

Aligning image to put face on the standard position

Aligning image to put face on the standard position

Creates an instance of this class with given parameters

Creates an instance of this class with given parameters

Extracting face feature from aligned image

Extracting face feature from aligned image

Calculating the distance between two face features

Calculating the distance between two face features

Link to this section cv

Link to this function

alignCrop(self, src_img, face_box)

View Source

Aligning image to put face on the standard position

Positional Arguments
  • src_img: Evision.Mat.

    input image

  • face_box: Evision.Mat.

    the detection result used for indicate face in input image

Return

Python prototype (for reference):

alignCrop(src_img, face_box[, aligned_img]) -> aligned_img
Link to this function

alignCrop(self, src_img, face_box, opts)

View Source

Aligning image to put face on the standard position

Positional Arguments
  • src_img: Evision.Mat.

    input image

  • face_box: Evision.Mat.

    the detection result used for indicate face in input image

Return

Python prototype (for reference):

alignCrop(src_img, face_box[, aligned_img]) -> aligned_img

Creates an instance of this class with given parameters

Positional Arguments
  • model: String.

    the path of the onnx model used for face recognition

  • config: String.

    the path to the config file for compability, which is not requested for ONNX models

Keyword Arguments
  • backend_id: int.

    the id of backend

  • target_id: int.

    the id of target device

Python prototype (for reference):

create(model, config[, backend_id[, target_id]]) -> retval
Link to this function

create(model, config, opts)

View Source

Creates an instance of this class with given parameters

Positional Arguments
  • model: String.

    the path of the onnx model used for face recognition

  • config: String.

    the path to the config file for compability, which is not requested for ONNX models

Keyword Arguments
  • backend_id: int.

    the id of backend

  • target_id: int.

    the id of target device

Python prototype (for reference):

create(model, config[, backend_id[, target_id]]) -> retval
Link to this function

feature(self, aligned_img)

View Source

Extracting face feature from aligned image

Positional Arguments
Return

Python prototype (for reference):

feature(aligned_img[, face_feature]) -> face_feature
Link to this function

feature(self, aligned_img, opts)

View Source

Extracting face feature from aligned image

Positional Arguments
Return

Python prototype (for reference):

feature(aligned_img[, face_feature]) -> face_feature
Link to this function

match(self, face_feature1, face_feature2)

View Source

Calculating the distance between two face features

Positional Arguments
  • face_feature1: Evision.Mat.

    the first input feature

  • face_feature2: Evision.Mat.

    the second input feature of the same size and the same type as face_feature1

Keyword Arguments
  • dis_type: int.

    defining the similarity with optional values "FR_OSINE" or "FR_NORM_L2"

Python prototype (for reference):

match(face_feature1, face_feature2[, dis_type]) -> retval
Link to this function

match(self, face_feature1, face_feature2, opts)

View Source

Calculating the distance between two face features

Positional Arguments
  • face_feature1: Evision.Mat.

    the first input feature

  • face_feature2: Evision.Mat.

    the second input feature of the same size and the same type as face_feature1

Keyword Arguments
  • dis_type: int.

    defining the similarity with optional values "FR_OSINE" or "FR_NORM_L2"

Python prototype (for reference):

match(face_feature1, face_feature2[, dis_type]) -> retval

Link to this section Functions

Link to this function

alignCrop!(self, src_img, face_box)

View Source

Raising version of alignCrop/3.

Link to this function

alignCrop!(self, src_img, face_box, opts)

View Source

Raising version of alignCrop/4.

Raising version of create/2.

Link to this function

create!(model, config, opts)

View Source

Raising version of create/3.

Link to this function

feature!(self, aligned_img)

View Source

Raising version of feature/2.

Link to this function

feature!(self, aligned_img, opts)

View Source

Raising version of feature/3.

Link to this function

match!(self, face_feature1, face_feature2)

View Source

Raising version of match/3.

Link to this function

match!(self, face_feature1, face_feature2, opts)

View Source

Raising version of match/4.