Package org.opencv.face
Class Facemark
java.lang.Object
org.opencv.core.Algorithm
org.opencv.face.Facemark
- Direct Known Subclasses:
FacemarkKazemi
,FacemarkTrain
Abstract base class for all facemark models
To utilize this API in your program, please take a look at the REF: tutorial_table_of_content_facemark
### Description
Facemark is a base class which provides universal access to any specific facemark algorithm.
Therefore, the users should declare a desired algorithm before they can use it in their application.
Here is an example on how to declare a facemark algorithm:
// Using Facemark in your code:
Ptr<Facemark> facemark = createFacemarkLBF();
The typical pipeline for facemark detection is as follows:
- Load the trained model using Facemark::loadModel.
- Perform the fitting on an image via Facemark::fit.
-
Field Summary
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionstatic Facemark
__fromPtr__
(long addr) protected void
finalize()
boolean
fit
(Mat image, MatOfRect faces, List<MatOfPoint2f> landmarks) Detect facial landmarks from an image.void
A function to load the trained model before the fitting process.Methods inherited from class org.opencv.core.Algorithm
clear, empty, getDefaultName, getNativeObjAddr, save
-
Constructor Details
-
Facemark
protected Facemark(long addr)
-
-
Method Details
-
__fromPtr__
-
loadModel
A function to load the trained model before the fitting process.- Parameters:
model
- A string represent the filename of a trained model. <B>Example of usage</B>facemark->loadModel("../data/lbf.model");
-
fit
Detect facial landmarks from an image.- Parameters:
image
- Input image.faces
- Output of the function which represent region of interest of the detected faces. Each face is stored in cv::Rect container.landmarks
- The detected landmark points for each faces. <B>Example of usage</B>Mat image = imread("image.jpg"); std::vector<Rect> faces; std::vector<std::vector<Point2f> > landmarks; facemark->fit(image, faces, landmarks);
- Returns:
- automatically generated
-
finalize
-