org.opencv.ml
Class CvSVM

java.lang.Object
  org.opencv.ml.CvStatModel
      org.opencv.ml.CvSVM

public class CvSVM
extends CvStatModel

Support Vector Machines.

See Also:

org.opencv.ml.CvSVM : public CvStatModel

Field Summary

static int	C
static int	C_SVC
static int	COEF
static int	DEGREE
static int	EPS_SVR
static int	GAMMA
static int	LINEAR
static int	NU
static int	NU_SVC
static int	NU_SVR
static int	ONE_CLASS
static int	P
static int	POLY
static int	RBF
static int	SIGMOID

Fields inherited from class org.opencv.ml.CvStatModel

nativeObj

Constructor Summary

	CvSVM() Default and training constructors.
protected	CvSVM(long addr)
	CvSVM(Mat trainData, Mat responses) Default and training constructors.
	CvSVM(Mat trainData, Mat responses, Mat varIdx, Mat sampleIdx, CvSVMParams params) Default and training constructors.

Method Summary

void	clear()
protected void	finalize()
int	get_support_vector_count()
int	get_var_count() Returns the number of used features (variables count).
void	predict_all(Mat samples, Mat results) Predicts the response for input sample(s).
float	predict(Mat sample) Predicts the response for input sample(s).
float	predict(Mat sample, boolean returnDFVal) Predicts the response for input sample(s).
boolean	train_auto(Mat trainData, Mat responses, Mat varIdx, Mat sampleIdx, CvSVMParams params) Trains an SVM with optimal parameters.
boolean	train_auto(Mat trainData, Mat responses, Mat varIdx, Mat sampleIdx, CvSVMParams params, int k_fold, CvParamGrid Cgrid, CvParamGrid gammaGrid, CvParamGrid pGrid, CvParamGrid nuGrid, CvParamGrid coeffGrid, CvParamGrid degreeGrid, boolean balanced) Trains an SVM with optimal parameters.
boolean	train(Mat trainData, Mat responses) Trains an SVM.
boolean	train(Mat trainData, Mat responses, Mat varIdx, Mat sampleIdx, CvSVMParams params) Trains an SVM.

Methods inherited from class org.opencv.ml.CvStatModel

load, load, save, save

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

C

public static final int C

See Also:

Constant Field Values

C_SVC

public static final int C_SVC

See Also:

Constant Field Values

COEF

public static final int COEF

See Also:

Constant Field Values

DEGREE

public static final int DEGREE

See Also:

Constant Field Values

EPS_SVR

public static final int EPS_SVR

See Also:

Constant Field Values

GAMMA

public static final int GAMMA

See Also:

Constant Field Values

LINEAR

public static final int LINEAR

See Also:

Constant Field Values

NU

public static final int NU

See Also:

Constant Field Values

NU_SVC

public static final int NU_SVC

See Also:

Constant Field Values

NU_SVR

public static final int NU_SVR

See Also:

Constant Field Values

ONE_CLASS

public static final int ONE_CLASS

See Also:

Constant Field Values

P

public static final int P

See Also:

Constant Field Values

POLY

public static final int POLY

See Also:

Constant Field Values

RBF

public static final int RBF

See Also:

Constant Field Values

SIGMOID

public static final int SIGMOID

See Also:

Constant Field Values

Constructor Detail

CvSVM

public CvSVM()

Default and training constructors.

The constructors follow conventions of "CvStatModel.CvStatModel". See "CvStatModel.train" for parameters descriptions.

See Also:

org.opencv.ml.CvSVM.CvSVM

CvSVM

protected CvSVM(long addr)

CvSVM

public CvSVM(Mat trainData,
             Mat responses)

Default and training constructors.

The constructors follow conventions of "CvStatModel.CvStatModel". See "CvStatModel.train" for parameters descriptions.

Parameters:

trainData - a trainData

responses - a responses

See Also:

org.opencv.ml.CvSVM.CvSVM

CvSVM

public CvSVM(Mat trainData,
             Mat responses,
             Mat varIdx,
             Mat sampleIdx,
             CvSVMParams params)

Default and training constructors.

The constructors follow conventions of "CvStatModel.CvStatModel". See "CvStatModel.train" for parameters descriptions.

Parameters:

trainData - a trainData

responses - a responses

varIdx - a varIdx

sampleIdx - a sampleIdx

params - a params

See Also:

org.opencv.ml.CvSVM.CvSVM

Method Detail

clear

public void clear()

finalize

protected void finalize()
                 throws java.lang.Throwable

Overrides:

finalize in class CvStatModel

Throws:

java.lang.Throwable

get_support_vector_count

public int get_support_vector_count()

get_var_count

public int get_var_count()

Returns the number of used features (variables count).

See Also:

org.opencv.ml.CvSVM.get_var_count

predict_all

public void predict_all(Mat samples,
                        Mat results)

Predicts the response for input sample(s).

If you pass one sample then prediction result is returned. If you want to get responses for several samples then you should pass the results matrix where prediction results will be stored.

The function is parallelized with the TBB library.

Parameters:

samples - Input samples for prediction.

results - Output prediction responses for corresponding samples.

See Also:

org.opencv.ml.CvSVM.predict

predict

public float predict(Mat sample)

Predicts the response for input sample(s).

If you pass one sample then prediction result is returned. If you want to get responses for several samples then you should pass the results matrix where prediction results will be stored.

The function is parallelized with the TBB library.

Parameters:

sample - Input sample for prediction.

See Also:

org.opencv.ml.CvSVM.predict

predict

public float predict(Mat sample,
                     boolean returnDFVal)

Predicts the response for input sample(s).

If you pass one sample then prediction result is returned. If you want to get responses for several samples then you should pass the results matrix where prediction results will be stored.

The function is parallelized with the TBB library.

Parameters:

sample - Input sample for prediction.

returnDFVal - Specifies a type of the return value. If true and the problem is 2-class classification then the method returns the decision function value that is signed distance to the margin, else the function returns a class label (classification) or estimated function value (regression).

See Also:

org.opencv.ml.CvSVM.predict

train_auto

public boolean train_auto(Mat trainData,
                          Mat responses,
                          Mat varIdx,
                          Mat sampleIdx,
                          CvSVMParams params)

Trains an SVM with optimal parameters.

The method trains the SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree from "CvSVMParams". Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

If there is no need to optimize a parameter, the corresponding grid step should be set to any value less than or equal to 1. For example, to avoid optimization in gamma, set gamma_grid.step = 0, gamma_grid.min_val, gamma_grid.max_val as arbitrary numbers. In this case, the value params.gamma is taken for gamma.

And, finally, if the optimization in a parameter is required but the corresponding grid is unknown, you may call the function "CvSVM.get_default_grid". To generate a grid, for example, for gamma, call CvSVM.get_default_grid(CvSVM.GAMMA).

This function works for the classification (params.svm_type=CvSVM.C_SVC or params.svm_type=CvSVM.NU_SVC) as well as for the regression (params.svm_type=CvSVM.EPS_SVR or params.svm_type=CvSVM.NU_SVR). If params.svm_type=CvSVM.ONE_CLASS, no optimization is made and the usual SVM with parameters specified in params is executed.

Parameters:

trainData - a trainData

responses - a responses

varIdx - a varIdx

sampleIdx - a sampleIdx

params - a params

See Also:

org.opencv.ml.CvSVM.train_auto

train_auto

public boolean train_auto(Mat trainData,
                          Mat responses,
                          Mat varIdx,
                          Mat sampleIdx,
                          CvSVMParams params,
                          int k_fold,
                          CvParamGrid Cgrid,
                          CvParamGrid gammaGrid,
                          CvParamGrid pGrid,
                          CvParamGrid nuGrid,
                          CvParamGrid coeffGrid,
                          CvParamGrid degreeGrid,
                          boolean balanced)

Trains an SVM with optimal parameters.

The method trains the SVM model automatically by choosing the optimal parameters C, gamma, p, nu, coef0, degree from "CvSVMParams". Parameters are considered optimal when the cross-validation estimate of the test set error is minimal.

If there is no need to optimize a parameter, the corresponding grid step should be set to any value less than or equal to 1. For example, to avoid optimization in gamma, set gamma_grid.step = 0, gamma_grid.min_val, gamma_grid.max_val as arbitrary numbers. In this case, the value params.gamma is taken for gamma.

And, finally, if the optimization in a parameter is required but the corresponding grid is unknown, you may call the function "CvSVM.get_default_grid". To generate a grid, for example, for gamma, call CvSVM.get_default_grid(CvSVM.GAMMA).

This function works for the classification (params.svm_type=CvSVM.C_SVC or params.svm_type=CvSVM.NU_SVC) as well as for the regression (params.svm_type=CvSVM.EPS_SVR or params.svm_type=CvSVM.NU_SVR). If params.svm_type=CvSVM.ONE_CLASS, no optimization is made and the usual SVM with parameters specified in params is executed.

Parameters:

trainData - a trainData

responses - a responses

varIdx - a varIdx

sampleIdx - a sampleIdx

params - a params

k_fold - Cross-validation parameter. The training set is divided into k_fold subsets. One subset is used to test the model, the others form the train set. So, the SVM algorithm is executed k_fold times.

Cgrid - a Cgrid

gammaGrid - Iteration grid for the corresponding SVM parameter.

pGrid - Iteration grid for the corresponding SVM parameter.

nuGrid - Iteration grid for the corresponding SVM parameter.

coeffGrid - Iteration grid for the corresponding SVM parameter.

degreeGrid - Iteration grid for the corresponding SVM parameter.

balanced - If true and the problem is 2-class classification then the method creates more balanced cross-validation subsets that is proportions between classes in subsets are close to such proportion in the whole train dataset.

See Also:

org.opencv.ml.CvSVM.train_auto

train

public boolean train(Mat trainData,
                     Mat responses)

Trains an SVM.

The method trains the SVM model. It follows the conventions of the generic "CvStatModel.train" approach with the following limitations:

• Only the CV_ROW_SAMPLE data layout is supported.
• Input variables are all ordered.
• Output variables can be either categorical (params.svm_type=CvSVM.C_SVC or params.svm_type=CvSVM.NU_SVC), or ordered (params.svm_type=CvSVM.EPS_SVR or params.svm_type=CvSVM.NU_SVR), or not required at all (params.svm_type=CvSVM.ONE_CLASS).
• Missing measurements are not supported.

All the other parameters are gathered in the "CvSVMParams" structure.

Parameters:

trainData - a trainData

responses - a responses

See Also:

org.opencv.ml.CvSVM.train

train

public boolean train(Mat trainData,
                     Mat responses,
                     Mat varIdx,
                     Mat sampleIdx,
                     CvSVMParams params)

Trains an SVM.

The method trains the SVM model. It follows the conventions of the generic "CvStatModel.train" approach with the following limitations:

• Only the CV_ROW_SAMPLE data layout is supported.
• Input variables are all ordered.
• Output variables can be either categorical (params.svm_type=CvSVM.C_SVC or params.svm_type=CvSVM.NU_SVC), or ordered (params.svm_type=CvSVM.EPS_SVR or params.svm_type=CvSVM.NU_SVR), or not required at all (params.svm_type=CvSVM.ONE_CLASS).
• Missing measurements are not supported.

All the other parameters are gathered in the "CvSVMParams" structure.

Parameters:

trainData - a trainData

responses - a responses

varIdx - a varIdx

sampleIdx - a sampleIdx

params - a params

See Also:

org.opencv.ml.CvSVM.train