8 * An example using the FaceRecognizer class can be found at opencv_source_code/samples/cpp/facerec_demo.cpp
10 * (Python) An example using the FaceRecognizer class can be found at opencv_source_code/samples/python2/facerec_demo.py
15 .. ocv:class:: FaceRecognizer : public Algorithm
17 All face recognition models in OpenCV are derived from the abstract base class :ocv:class:`FaceRecognizer`, which provides
18 a unified access to all face recongition algorithms in OpenCV. ::
20 class FaceRecognizer : public Algorithm
23 //! virtual destructor
24 virtual ~FaceRecognizer() {}
26 // Trains a FaceRecognizer.
27 virtual void train(InputArray src, InputArray labels) = 0;
29 // Updates a FaceRecognizer.
30 virtual void update(InputArrayOfArrays src, InputArray labels);
32 // Gets a prediction from a FaceRecognizer.
33 virtual int predict(InputArray src) const = 0;
35 // Predicts the label and confidence for a given sample.
36 virtual void predict(InputArray src, int &label, double &confidence) const = 0;
38 // Serializes this object to a given filename.
39 virtual void save(const string& filename) const;
41 // Deserializes this object from a given filename.
42 virtual void load(const string& filename);
44 // Serializes this object to a given cv::FileStorage.
45 virtual void save(FileStorage& fs) const = 0;
47 // Deserializes this object from a given cv::FileStorage.
48 virtual void load(const FileStorage& fs) = 0;
55 I'll go a bit more into detail explaining :ocv:class:`FaceRecognizer`, because it doesn't look like a powerful interface at first sight. But: Every :ocv:class:`FaceRecognizer` is an :ocv:class:`Algorithm`, so you can easily get/set all model internals (if allowed by the implementation). :ocv:class:`Algorithm` is a relatively new OpenCV concept, which is available since the 2.4 release. I suggest you take a look at its description.
57 :ocv:class:`Algorithm` provides the following features for all derived classes:
59 * So called “virtual constructor”. That is, each Algorithm derivative is registered at program start and you can get the list of registered algorithms and create instance of a particular algorithm by its name (see :ocv:func:`Algorithm::create`). If you plan to add your own algorithms, it is good practice to add a unique prefix to your algorithms to distinguish them from other algorithms.
61 * Setting/Retrieving algorithm parameters by name. If you used video capturing functionality from OpenCV highgui module, you are probably familar with :ocv:cfunc:`cvSetCaptureProperty`, :ocv:cfunc:`cvGetCaptureProperty`, :ocv:func:`VideoCapture::set` and :ocv:func:`VideoCapture::get`. :ocv:class:`Algorithm` provides similar method where instead of integer id's you specify the parameter names as text strings. See :ocv:func:`Algorithm::set` and :ocv:func:`Algorithm::get` for details.
63 * Reading and writing parameters from/to XML or YAML files. Every Algorithm derivative can store all its parameters and then read them back. There is no need to re-implement it each time.
65 Moreover every :ocv:class:`FaceRecognizer` supports the:
67 * **Training** of a :ocv:class:`FaceRecognizer` with :ocv:func:`FaceRecognizer::train` on a given set of images (your face database!).
69 * **Prediction** of a given sample image, that means a face. The image is given as a :ocv:class:`Mat`.
71 * **Loading/Saving** the model state from/to a given XML or YAML.
73 Setting the Thresholds
74 +++++++++++++++++++++++
76 Sometimes you run into the situation, when you want to apply a threshold on the prediction. A common scenario in face recognition is to tell, wether a face belongs to the training dataset or if it is unknown. You might wonder, why there's no public API in :ocv:class:`FaceRecognizer` to set the threshold for the prediction, but rest assured: It's supported. It just means there's no generic way in an abstract class to provide an interface for setting/getting the thresholds of *every possible* :ocv:class:`FaceRecognizer` algorithm. The appropriate place to set the thresholds is in the constructor of the specific :ocv:class:`FaceRecognizer` and since every :ocv:class:`FaceRecognizer` is a :ocv:class:`Algorithm` (see above), you can get/set the thresholds at runtime!
78 Here is an example of setting a threshold for the Eigenfaces method, when creating the model:
82 // Let's say we want to keep 10 Eigenfaces and have a threshold value of 10.0
83 int num_components = 10;
84 double threshold = 10.0;
85 // Then if you want to have a cv::FaceRecognizer with a confidence threshold,
86 // create the concrete implementation with the appropiate parameters:
87 Ptr<FaceRecognizer> model = createEigenFaceRecognizer(num_components, threshold);
89 Sometimes it's impossible to train the model, just to experiment with threshold values. Thanks to :ocv:class:`Algorithm` it's possible to set internal model thresholds during runtime. Let's see how we would set/get the prediction for the Eigenface model, we've created above:
93 // The following line reads the threshold from the Eigenfaces model:
94 double current_threshold = model->getDouble("threshold");
95 // And this line sets the threshold to 0.0:
96 model->set("threshold", 0.0);
98 If you've set the threshold to ``0.0`` as we did above, then:
103 Mat img = imread("person1/3.jpg", CV_LOAD_IMAGE_GRAYSCALE);
104 // Get a prediction from the model. Note: We've set a threshold of 0.0 above,
105 // since the distance is almost always larger than 0.0, you'll get -1 as
106 // label, which indicates, this face is unknown
107 int predicted_label = model->predict(img);
110 is going to yield ``-1`` as predicted label, which states this face is unknown.
112 Getting the name of a FaceRecognizer
113 +++++++++++++++++++++++++++++++++++++
115 Since every :ocv:class:`FaceRecognizer` is a :ocv:class:`Algorithm`, you can use :ocv:func:`Algorithm::name` to get the name of a :ocv:class:`FaceRecognizer`:
119 // Create a FaceRecognizer:
120 Ptr<FaceRecognizer> model = createEigenFaceRecognizer();
121 // And here's how to get its name:
122 std::string name = model->name();
125 FaceRecognizer::train
126 ---------------------
128 Trains a FaceRecognizer with given data and associated labels.
130 .. ocv:function:: void FaceRecognizer::train( InputArrayOfArrays src, InputArray labels ) = 0
132 :param src: The training images, that means the faces you want to learn. The data has to be given as a ``vector<Mat>``.
134 :param labels: The labels corresponding to the images have to be given either as a ``vector<int>`` or a
136 The following source code snippet shows you how to learn a Fisherfaces model on a given set of images. The images are read with :ocv:func:`imread` and pushed into a ``std::vector<Mat>``. The labels of each image are stored within a ``std::vector<int>`` (you could also use a :ocv:class:`Mat` of type `CV_32SC1`). Think of the label as the subject (the person) this image belongs to, so same subjects (persons) should have the same label. For the available :ocv:class:`FaceRecognizer` you don't have to pay any attention to the order of the labels, just make sure same persons have the same label:
140 // holds images and labels
143 // images for first person
144 images.push_back(imread("person0/0.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(0);
145 images.push_back(imread("person0/1.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(0);
146 images.push_back(imread("person0/2.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(0);
147 // images for second person
148 images.push_back(imread("person1/0.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(1);
149 images.push_back(imread("person1/1.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(1);
150 images.push_back(imread("person1/2.jpg", CV_LOAD_IMAGE_GRAYSCALE)); labels.push_back(1);
152 Now that you have read some images, we can create a new :ocv:class:`FaceRecognizer`. In this example I'll create a Fisherfaces model and decide to keep all of the possible Fisherfaces:
156 // Create a new Fisherfaces model and retain all available Fisherfaces,
157 // this is the most common usage of this specific FaceRecognizer:
159 Ptr<FaceRecognizer> model = createFisherFaceRecognizer();
161 And finally train it on the given dataset (the face images and labels):
165 // This is the common interface to train all of the available cv::FaceRecognizer
168 model->train(images, labels);
170 FaceRecognizer::update
171 ----------------------
173 Updates a FaceRecognizer with given data and associated labels.
175 .. ocv:function:: void FaceRecognizer::update( InputArrayOfArrays src, InputArray labels )
177 :param src: The training images, that means the faces you want to learn. The data has to be given as a ``vector<Mat>``.
179 :param labels: The labels corresponding to the images have to be given either as a ``vector<int>`` or a
181 This method updates a (probably trained) :ocv:class:`FaceRecognizer`, but only if the algorithm supports it. The Local Binary Patterns Histograms (LBPH) recognizer (see :ocv:func:`createLBPHFaceRecognizer`) can be updated. For the Eigenfaces and Fisherfaces method, this is algorithmically not possible and you have to re-estimate the model with :ocv:func:`FaceRecognizer::train`. In any case, a call to train empties the existing model and learns a new model, while update does not delete any model data.
185 // Create a new LBPH model (it can be updated) and use the default parameters,
186 // this is the most common usage of this specific FaceRecognizer:
188 Ptr<FaceRecognizer> model = createLBPHFaceRecognizer();
189 // This is the common interface to train all of the available cv::FaceRecognizer
192 model->train(images, labels);
193 // Some containers to hold new image:
194 vector<Mat> newImages;
195 vector<int> newLabels;
196 // You should add some images to the containers:
200 // Now updating the model is as easy as calling:
201 model->update(newImages,newLabels);
202 // This will preserve the old model data and extend the existing model
203 // with the new features extracted from newImages!
205 Calling update on an Eigenfaces model (see :ocv:func:`createEigenFaceRecognizer`), which doesn't support updating, will throw an error similar to:
209 OpenCV Error: The function/feature is not implemented (This FaceRecognizer (FaceRecognizer.Eigenfaces) does not support updating, you have to use FaceRecognizer::train to update it.) in update, file /home/philipp/git/opencv/modules/contrib/src/facerec.cpp, line 305
210 terminate called after throwing an instance of 'cv::Exception'
212 Please note: The :ocv:class:`FaceRecognizer` does not store your training images, because this would be very memory intense and it's not the responsibility of te :ocv:class:`FaceRecognizer` to do so. The caller is responsible for maintaining the dataset, he want to work with.
214 FaceRecognizer::predict
215 -----------------------
217 .. ocv:function:: int FaceRecognizer::predict( InputArray src ) const = 0
218 .. ocv:function:: void FaceRecognizer::predict( InputArray src, int & label, double & confidence ) const = 0
220 Predicts a label and associated confidence (e.g. distance) for a given input image.
222 :param src: Sample image to get a prediction from.
223 :param label: The predicted label for the given image.
224 :param confidence: Associated confidence (e.g. distance) for the predicted label.
226 The suffix ``const`` means that prediction does not affect the internal model
227 state, so the method can be safely called from within different threads.
229 The following example shows how to get a prediction from a trained model:
234 // Do your initialization here (create the cv::FaceRecognizer model) ...
236 // Read in a sample image:
237 Mat img = imread("person1/3.jpg", CV_LOAD_IMAGE_GRAYSCALE);
238 // And get a prediction from the cv::FaceRecognizer:
239 int predicted = model->predict(img);
241 Or to get a prediction and the associated confidence (e.g. distance):
246 // Do your initialization here (create the cv::FaceRecognizer model) ...
248 Mat img = imread("person1/3.jpg", CV_LOAD_IMAGE_GRAYSCALE);
249 // Some variables for the predicted label and associated confidence (e.g. distance):
250 int predicted_label = -1;
251 double predicted_confidence = 0.0;
252 // Get the prediction and associated confidence from the model
253 model->predict(img, predicted_label, predicted_confidence);
258 Saves a :ocv:class:`FaceRecognizer` and its model state.
260 .. ocv:function:: void FaceRecognizer::save(const string& filename) const
262 Saves this model to a given filename, either as XML or YAML.
264 :param filename: The filename to store this :ocv:class:`FaceRecognizer` to (either XML/YAML).
266 .. ocv:function:: void FaceRecognizer::save(FileStorage& fs) const
268 Saves this model to a given :ocv:class:`FileStorage`.
270 :param fs: The :ocv:class:`FileStorage` to store this :ocv:class:`FaceRecognizer` to.
273 Every :ocv:class:`FaceRecognizer` overwrites ``FaceRecognizer::save(FileStorage& fs)``
274 to save the internal model state. ``FaceRecognizer::save(const string& filename)`` saves
275 the state of a model to the given filename.
277 The suffix ``const`` means that prediction does not affect the internal model
278 state, so the method can be safely called from within different threads.
283 Loads a :ocv:class:`FaceRecognizer` and its model state.
285 .. ocv:function:: void FaceRecognizer::load( const string& filename )
286 .. ocv:function:: void FaceRecognizer::load( const FileStorage& fs ) = 0
288 Loads a persisted model and state from a given XML or YAML file . Every
289 :ocv:class:`FaceRecognizer` has to overwrite ``FaceRecognizer::load(FileStorage& fs)``
290 to enable loading the model state. ``FaceRecognizer::load(FileStorage& fs)`` in
291 turn gets called by ``FaceRecognizer::load(const string& filename)``, to ease
294 createEigenFaceRecognizer
295 -------------------------
297 .. ocv:function:: Ptr<FaceRecognizer> createEigenFaceRecognizer(int num_components = 0, double threshold = DBL_MAX)
299 :param num_components: The number of components (read: Eigenfaces) kept for this Prinicpal Component Analysis. As a hint: There's no rule how many components (read: Eigenfaces) should be kept for good reconstruction capabilities. It is based on your input data, so experiment with the number. Keeping 80 components should almost always be sufficient.
301 :param threshold: The threshold applied in the prediciton.
306 * Training and prediction must be done on grayscale images, use :ocv:func:`cvtColor` to convert between the color spaces.
307 * **THE EIGENFACES METHOD MAKES THE ASSUMPTION, THAT THE TRAINING AND TEST IMAGES ARE OF EQUAL SIZE.** (caps-lock, because I got so many mails asking for this). You have to make sure your input data has the correct shape, else a meaningful exception is thrown. Use :ocv:func:`resize` to resize the images.
308 * This model does not support updating.
313 * ``num_components`` see :ocv:func:`createEigenFaceRecognizer`.
314 * ``threshold`` see :ocv:func:`createEigenFaceRecognizer`.
315 * ``eigenvalues`` The eigenvalues for this Principal Component Analysis (ordered descending).
316 * ``eigenvectors`` The eigenvectors for this Principal Component Analysis (ordered by their eigenvalue).
317 * ``mean`` The sample mean calculated from the training data.
318 * ``projections`` The projections of the training data.
319 * ``labels`` The threshold applied in the prediction. If the distance to the nearest neighbor is larger than the threshold, this method returns -1.
321 createFisherFaceRecognizer
322 --------------------------
324 .. ocv:function:: Ptr<FaceRecognizer> createFisherFaceRecognizer(int num_components = 0, double threshold = DBL_MAX)
326 :param num_components: The number of components (read: Fisherfaces) kept for this Linear Discriminant Analysis with the Fisherfaces criterion. It's useful to keep all components, that means the number of your classes ``c`` (read: subjects, persons you want to recognize). If you leave this at the default (``0``) or set it to a value less-equal ``0`` or greater ``(c-1)``, it will be set to the correct number ``(c-1)`` automatically.
328 :param threshold: The threshold applied in the prediction. If the distance to the nearest neighbor is larger than the threshold, this method returns -1.
333 * Training and prediction must be done on grayscale images, use :ocv:func:`cvtColor` to convert between the color spaces.
334 * **THE FISHERFACES METHOD MAKES THE ASSUMPTION, THAT THE TRAINING AND TEST IMAGES ARE OF EQUAL SIZE.** (caps-lock, because I got so many mails asking for this). You have to make sure your input data has the correct shape, else a meaningful exception is thrown. Use :ocv:func:`resize` to resize the images.
335 * This model does not support updating.
340 * ``num_components`` see :ocv:func:`createFisherFaceRecognizer`.
341 * ``threshold`` see :ocv:func:`createFisherFaceRecognizer`.
342 * ``eigenvalues`` The eigenvalues for this Linear Discriminant Analysis (ordered descending).
343 * ``eigenvectors`` The eigenvectors for this Linear Discriminant Analysis (ordered by their eigenvalue).
344 * ``mean`` The sample mean calculated from the training data.
345 * ``projections`` The projections of the training data.
346 * ``labels`` The labels corresponding to the projections.
349 createLBPHFaceRecognizer
350 -------------------------
352 .. ocv:function:: Ptr<FaceRecognizer> createLBPHFaceRecognizer(int radius=1, int neighbors=8, int grid_x=8, int grid_y=8, double threshold = DBL_MAX)
354 :param radius: The radius used for building the Circular Local Binary Pattern. The greater the radius, the
355 :param neighbors: The number of sample points to build a Circular Local Binary Pattern from. An appropriate value is to use `` 8`` sample points. Keep in mind: the more sample points you include, the higher the computational cost.
356 :param grid_x: The number of cells in the horizontal direction, ``8`` is a common value used in publications. The more cells, the finer the grid, the higher the dimensionality of the resulting feature vector.
357 :param grid_y: The number of cells in the vertical direction, ``8`` is a common value used in publications. The more cells, the finer the grid, the higher the dimensionality of the resulting feature vector.
358 :param threshold: The threshold applied in the prediction. If the distance to the nearest neighbor is larger than the threshold, this method returns -1.
363 * The Circular Local Binary Patterns (used in training and prediction) expect the data given as grayscale images, use :ocv:func:`cvtColor` to convert between the color spaces.
364 * This model supports updating.
369 * ``radius`` see :ocv:func:`createLBPHFaceRecognizer`.
370 * ``neighbors`` see :ocv:func:`createLBPHFaceRecognizer`.
371 * ``grid_x`` see :ocv:func:`createLBPHFaceRecognizer`.
372 * ``grid_y`` see :ocv:func:`createLBPHFaceRecognizer`.
373 * ``threshold`` see :ocv:func:`createLBPHFaceRecognizer`.
374 * ``histograms`` Local Binary Patterns Histograms calculated from the given training data (empty if none was given).
375 * ``labels`` Labels corresponding to the calculated Local Binary Patterns Histograms.