C++ API Documentation

Tracker class

class FaceVerifier

The Face Verifier class.

Public Functions

FaceVerifier(const std::string &modelFile, int maxConcurrency = 0)

Constructor: loads model file, sets up the processing.

Parameters

  • model_file: path for the used model

  • max_concurrency: maximum allowed concurrency, 0 means automatic (using all cores), default: 0

~FaceVerifier()

Destructor.

std::future<std::vector<fvl::Face>> detectFaces(const fvl::ImageHeader &imageHeader)

Detects the faces on an image with the std::future API.

Note

The given ImageHeader doesn’t own the image data, and it is safe to delete the data after the call, a copy is happening internally. See fvl::ImageHeader for details.

Note

Calling this function is non-blocking, so calling it again with the next image without waiting for the result is possible. Also see getConcurrentCalculations().

Note

This is the std::future based API, for callback API see fvl::FaceVerifier::detectFaces(const fvl::ImageHeader&, std::function<void (ResultOrError<std::vector<Face>>)>).

Parameters

  • imageHeader: image descriptor

void detectFaces(const fvl::ImageHeader &imageHeader, std::function<void(ResultOrError<std::vector<Face>>)> callback)

Detects the faces on an image with a callback API.

Note

The given ImageHeader doesn’t own the image data, and it is safe to delete the data after the call, a copy is happening internally. See fvl::ImageHeader for details.

Note

Calling this function is non-blocking, so calling it again with the next frame without waiting for the result is possible. Also see getConcurrentCalculations().

Note

This is the callback based API, for std::future API see fvl::FaceVerifier::detectFaces(const fvl::ImageHeader&).

Return

tracked landmarks and emotions

Parameters

  • imageHeader: image descriptor

  • callback: callback to call with the result

std::future<std::vector<float>> embedFace(const fvl::Face &face)

Returns the embedding of the detected face.

Note

Calling this function is non-blocking, so calling it again with the next frame without waiting for the result is possible. Also see getConcurrentCalculations().

Note

This is the std::future based API, for callback API see fvl::FaceVerifier::embedFace(const fvl::Face&, std::function<void (ResultOrError<std::vector<float>>)>).

Return

face embedding vector

Parameters

  • face: the previously detected face to embed

void embedFace(const fvl::Face &face, std::function<void(ResultOrError<std::vector<float>>)> callback)

Returns the embedding of the detected face.

Note

Calling this function is non-blocking, so calling it again with the next frame without waiting for the result is possible. Also see getConcurrentCalculations().

Note

This is the callback based API, for std::future API see fvl::FaceVerifier::embedFace(const fvl::Face&).

Parameters

  • face: the previously detected face to embed

  • callback: callback to call with the result

fvl::Match compareFaces(const std::vector<float> &embedding1, const std::vector<float> &embedding2)

Compares two embeddings.

Return

match object with the similarity metric

Parameters

  • embedding1: embedding of one of the faces to compare

  • embedding2: embedding of the other face to compare

int getConcurrentCalculations() const

Returns the value of the atomic counter for the number of calculations currently running concurrently.

You can use this to limit the number of concurrent calculations.

Return

The (approximate) number of calculations currently in-flight.

std::string getModelName() const

Returns the name (version etc) of the loaded model.

Return

name of the model

Public Static Functions

static fvl::Version getSDKVersion()

Returns the version of the SDK (and not the model)

Return

version of the SDK

static std::string getSDKVersionString()

Returns the version string of the SDK (and not the model)

Return

version string of the SDK

Image header class

struct ImageHeader

Descriptor class for image data (non-owning)

Public Members

const uint8_t *data

pointer to the byte array of the image

int width

width of the image in pixels

int height

height of the image in pixels

int stride

length of one row of pixels in bytes (e.g: 3*width + padding)

fvl::ImageFormat format

image format

enum fvl::ImageFormat

Values:

Grayscale = 0

8-bit grayscale

RGB = 1

24-bit RGB

RGBA = 2

32-bit RGBA or 32-bit RGB_

BGR = 3

24-bit BGR

BGRA = 4

32-bit BGRA or 32-bit BGR_

Result classes

Face

See also: landmarks specification.

class Face

Face Class.

Public Functions

Face(const fvl::ImageHeader &imageHeader, const std::vector<fvl::Point2d> &landmarks, const fvl::BoundingBox &bbox = fvl::BoundingBox(), float confidence = 0.0f)

Constructor for the Face object to support 3rd party face detectors.

Parameters

  • imageHeader: image descriptor

  • landmarks: face landmarks

  • bbox: face bounding box

  • confidence: face detection confidence

~Face()

Destructor.

DetectionQuality detectionQuality() const

Returns the detection quality of the detected face.

Return

DetectionQuality

BoundingBox boundingBox() const

Returns the bounding box of the detected face.

Return

BoundingBox

float confidence() const

Returns the confidence value of the detected face.

Return

float

std::vector<fvl::Point2d> landmarks() const

Returns the landmarks of the face.

Return

std::vector<fvl::Point2d>

Point2d

struct Point2d

Point2d class for landmarks.

Public Members

float x

x coordinate of the point

float y

y coordinate of the point

BoundingBox

struct BoundingBox

Bounding Box class for the faces.

Public Members

int x

x coordinate of the top-left corner

int y

y coordinate of the top-left corner

int width

width of the bounding box in pixels

int height

height of the bounding box in pixels

Match

struct Match

Face match class.

Public Members

float similarity

similarity of the faces