Module opencv::ml

source ·
Expand description

§Machine Learning

The Machine Learning Library (MLL) is a set of classes and functions for statistical classification, regression, and clustering of data.

Most of the classification and regression algorithms are implemented as C++ classes. As the algorithms have different sets of features (like an ability to handle missing measurements or categorical input variables), there is a little common ground between the classes. This common ground is defined by the class cv::ml::StatModel that all the other ML classes are derived from.

See detailed overview here: [ml_intro].

Modules§

Structs§

  • ANN_MLP
    Artificial Neural Networks - Multi-Layer Perceptrons.
  • Boost
    Boosted tree classifier derived from DTrees
  • DTrees
    The class represents a single decision tree or a collection of decision trees.
  • DTrees_Node
    The class represents a decision tree node.
  • DTrees_Split
    The class represents split in a decision tree.
  • EM
    The class implements the Expectation Maximization algorithm.
  • KNearest
    The class implements K-Nearest Neighbors model
  • LogisticRegression
    Implements Logistic Regression classifier.
  • NormalBayesClassifier
    Bayes classifier for normally distributed data.
  • ParamGrid
    The structure represents the logarithmic grid range of statmodel parameters.
  • RTrees
    The class implements the random forest predictor.
  • SVM
    Support Vector Machines.
  • SVMSGD
    ! Stochastic Gradient Descent SVM classifier
  • SVM_Kernel
  • StatModel
    Base class for statistical models in OpenCV ML.
  • TrainData
    Class encapsulating training data.

Enums§

Constants§

  • ANN_MLP_ANNEAL
    The simulated annealing algorithm. See Kirkpatrick83 for details.
  • ANN_MLP_BACKPROP
    The back-propagation algorithm.
  • ANN_MLP_GAUSSIAN
    Gaussian function: inline formula
  • ANN_MLP_IDENTITY
    Identity function: inline formula
  • ANN_MLP_LEAKYRELU
    Leaky ReLU function: for x>0 inline formula and x<=0 inline formula
  • ANN_MLP_NO_INPUT_SCALE
    Do not normalize the input vectors. If this flag is not set, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation equal to 1. If the network is assumed to be updated frequently, the new training data could be much different from original one. In this case, you should take care of proper normalization.
  • ANN_MLP_NO_OUTPUT_SCALE
    Do not normalize the output vectors. If the flag is not set, the training algorithm normalizes each output feature independently, by transforming it to the certain range depending on the used activation function.
  • ANN_MLP_RELU
    ReLU function: inline formula
  • ANN_MLP_RPROP
    The RPROP algorithm. See RPROP93 for details.
  • ANN_MLP_SIGMOID_SYM
    Symmetrical sigmoid: inline formula
  • ANN_MLP_UPDATE_WEIGHTS
    Update the network weights, rather than compute them from scratch. In the latter case the weights are initialized using the Nguyen-Widrow algorithm.
  • Boost_DISCRETE
    Discrete AdaBoost.
  • Boost_GENTLE
    Gentle AdaBoost. It puts less weight on outlier data points and for that reason is often good with regression data.
  • Boost_LOGIT
    LogitBoost. It can produce good regression fits.
  • Boost_REAL
    Real AdaBoost. It is a technique that utilizes confidence-rated predictions and works well with categorical data.
  • COL_SAMPLE
    each training sample occupies a column of samples
  • DTrees_PREDICT_AUTO
  • DTrees_PREDICT_MASK
  • DTrees_PREDICT_MAX_VOTE
  • DTrees_PREDICT_SUM
  • EM_COV_MAT_DEFAULT
    A symmetric positively defined matrix. The number of free parameters in each matrix is about inline formula. It is not recommended to use this option, unless there is pretty accurate initial estimation of the parameters and/or a huge number of training samples.
  • EM_COV_MAT_DIAGONAL
    A diagonal matrix with positive diagonal elements. The number of free parameters is d for each matrix. This is most commonly used option yielding good estimation results.
  • EM_COV_MAT_GENERIC
    A symmetric positively defined matrix. The number of free parameters in each matrix is about inline formula. It is not recommended to use this option, unless there is pretty accurate initial estimation of the parameters and/or a huge number of training samples.
  • EM_COV_MAT_SPHERICAL
    A scaled identity matrix inline formula. There is the only parameter inline formula to be estimated for each matrix. The option may be used in special cases, when the constraint is relevant, or as a first step in the optimization (for example in case when the data is preprocessed with PCA). The results of such preliminary estimation may be passed again to the optimization procedure, this time with covMatType=EM::COV_MAT_DIAGONAL.
  • EM_DEFAULT_MAX_ITERS
  • EM_DEFAULT_NCLUSTERS
  • EM_START_AUTO_STEP
  • EM_START_E_STEP
  • EM_START_M_STEP
  • KNearest_BRUTE_FORCE
  • KNearest_KDTREE
  • LogisticRegression_BATCH
  • LogisticRegression_MINI_BATCH
    Set MiniBatchSize to a positive integer when using this method.
  • LogisticRegression_REG_DISABLE
    Regularization disabled
  • LogisticRegression_REG_L1
    %L1 norm
  • LogisticRegression_REG_L2
    %L2 norm
  • ROW_SAMPLE
    each training sample is a row of samples
  • SVMSGD_ASGD
    Average Stochastic Gradient Descent
  • SVMSGD_HARD_MARGIN
    More accurate for the case of linearly separable sets.
  • SVMSGD_SGD
    Stochastic Gradient Descent
  • SVMSGD_SOFT_MARGIN
    General case, suits to the case of non-linearly separable sets, allows outliers.
  • SVM_C
  • SVM_CHI2
    Exponential Chi2 kernel, similar to the RBF kernel: inline formula.
  • SVM_COEF
  • SVM_CUSTOM
    Returned by SVM::getKernelType in case when custom kernel has been set
  • SVM_C_SVC
    C-Support Vector Classification. n-class classification (n inline formula 2), allows imperfect separation of classes with penalty multiplier C for outliers.
  • SVM_DEGREE
  • SVM_EPS_SVR
    inline formula-Support Vector Regression. The distance between feature vectors from the training set and the fitting hyper-plane must be less than p. For outliers the penalty multiplier C is used.
  • SVM_GAMMA
  • SVM_INTER
    Histogram intersection kernel. A fast kernel. inline formula.
  • SVM_LINEAR
    Linear kernel. No mapping is done, linear discrimination (or regression) is done in the original feature space. It is the fastest option. inline formula.
  • SVM_NU
  • SVM_NU_SVC
    inline formula-Support Vector Classification. n-class classification with possible imperfect separation. Parameter inline formula (in the range 0..1, the larger the value, the smoother the decision boundary) is used instead of C.
  • SVM_NU_SVR
    inline formula-Support Vector Regression. inline formula is used instead of p. See LibSVM for details.
  • SVM_ONE_CLASS
    Distribution Estimation (One-class %SVM). All the training data are from the same class, %SVM builds a boundary that separates the class from the rest of the feature space.
  • SVM_P
  • SVM_POLY
    Polynomial kernel: inline formula.
  • SVM_RBF
    Radial basis function (RBF), a good choice in most cases. inline formula.
  • SVM_SIGMOID
    Sigmoid kernel: inline formula.
  • StatModel_COMPRESSED_INPUT
  • StatModel_PREPROCESSED_INPUT
  • StatModel_RAW_OUTPUT
    makes the method return the raw results (the sum), not the class label
  • StatModel_UPDATE_MODEL
  • TEST_ERROR
  • TRAIN_ERROR
  • VAR_CATEGORICAL
    categorical variables
  • VAR_NUMERICAL
    same as VAR_ORDERED
  • VAR_ORDERED
    ordered variables

Traits§

Functions§

Type Aliases§