Train Vector Classifier

Brief Description

Train a classifier based on labeled geometries and a list of features to consider.

Tags

Learning

Long Description

This application trains a classifier based on labeled geometries and a list of features to consider for classification.
This application is based on LibSVM, OpenCV Machine Learning (2.3.1 and later), and Shark ML The output of this application is a text model file, whose format corresponds to the ML model type chosen. There is no image nor vector data output.

Parameters

Input and output data (io): This group of parameters allows setting input and output data.
- Input Vector Data (io.vd): Input geometries used for training (note : all geometries from the layer will be used)
- Input XML image statistics file (io.stats): XML file containing mean and variance of each feature.
- Output model (io.out): Output file containing the model estimated (.txt format).
- Output confusion matrix or contingency table (io.confmatout): Output file containing the confusion matrix or contingency table (.csv format).The contingency table is output when we unsupervised algorithms is used otherwise the confusion matrix is output.

Layer Index (layer): Index of the layer to use in the input vector file.
Field names for training features. (feat): List of field names in the input vector data to be used as features for training.
Validation data (valid): This group of parameters defines validation data.
- Validation Vector Data (valid.vd): Geometries used for validation (must contain the same fields used for training, all geometries from the layer will be used)
- Layer Index (valid.layer): Index of the layer to use in the validation vector file.

Field containing the class integer label for supervision (cfield): Field containing the class id for supervision. The values in this field shall be cast into integers. Only geometries with this field available will be taken into account.
Verbose mode (v): Verbose mode, display the contingency table result.
Classifier to use for the training (classifier): Choice of the classifier to use for the training.
- LibSVM classifier (libsvm): This group of parameters allows setting SVM classifier parameters.
  - SVM Kernel Type (classifier.libsvm.k): SVM Kernel Type.
    - Linear (linear): Linear Kernel, no mapping is done, this is the fastest option.
    - Gaussian radial basis function (rbf): This kernel is a good choice in most of the case. It is an exponential function of the euclidian distance between the vectors.
    - Polynomial (poly): Polynomial Kernel, the mapping is a polynomial function.
    - Sigmoid (sigmoid): The kernel is a hyperbolic tangente function of the vectors.
  - SVM Model Type (classifier.libsvm.m): Type of SVM formulation.
    - C support vector classification (csvc): This formulation allows imperfect separation of classes. The penalty is set through the cost parameter C.
    - Nu support vector classification (nusvc): This formulation allows imperfect separation of classes. The penalty is set through the cost parameter Nu. As compared to C, Nu is harder to optimize, and may not be as fast.
    - Distribution estimation (One Class SVM) (oneclass): All the training data are from the same class, SVM builds a boundary that separates the class from the rest of the feature space.
  - Cost parameter C (classifier.libsvm.c): SVM models have a cost parameter C (1 by default) to control the trade-off between training errors and forcing rigid margins.
  - Cost parameter Nu (classifier.libsvm.nu): Cost parameter Nu, in the range 0..1, the larger the value, the smoother the decision.
  - Parameters optimization (classifier.libsvm.opt): SVM parameters optimization flag.
  - Probability estimation (classifier.libsvm.prob): Probability estimation flag.
- Boost classifier (boost): This group of parameters allows setting Boost classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/boosting.html}.
  - Boost Type (classifier.boost.t): Type of Boosting algorithm.
    - Discrete AdaBoost (discrete): This procedure trains the classifiers on weighted versions of the training sample, giving higher weight to cases that are currently misclassified. This is done for a sequence of weighter samples, and then the final classifier is defined as a linear combination of the classifier from each stage.
    - Real AdaBoost (technique using confidence-rated predictions and working well with categorical data) (real): Adaptation of the Discrete Adaboost algorithm with Real value
    - LogitBoost (technique producing good regression fits) (logit): This procedure is an adaptive Newton algorithm for fitting an additive logistic regression model. Beware it can produce numeric instability.
    - Gentle AdaBoost (technique setting less weight on outlier data points and, for that reason, being often good with regression data) (gentle): A modified version of the Real Adaboost algorithm, using Newton stepping rather than exact optimization at each step.
  - Weak count (classifier.boost.w): The number of weak classifiers.
  - Weight Trim Rate (classifier.boost.r): A threshold between 0 and 1 used to save computational time. Samples with summary weight <= (1 - weight_trim_rate) do not participate in the next iteration of training. Set this parameter to 0 to turn off this functionality.
  - Maximum depth of the tree (classifier.boost.m): Maximum depth of the tree.
- Decision Tree classifier (dt): This group of parameters allows setting Decision Tree classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/decision_trees.html}.
  - Maximum depth of the tree (classifier.dt.max): The training algorithm attempts to split each node while its depth is smaller than the maximum possible depth of the tree. The actual depth may be smaller if the other termination criteria are met, and/or if the tree is pruned.
  - Minimum number of samples in each node (classifier.dt.min): If the number of samples in a node is smaller than this parameter, then this node will not be split.
  - Termination criteria for regression tree (classifier.dt.ra): If all absolute differences between an estimated value in a node and the values of the train samples in this node are smaller than this regression accuracy parameter, then the node will not be split further.
  - Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split (classifier.dt.cat): Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split.
  - K-fold cross-validations (classifier.dt.f): If cv_folds > 1, then it prunes a tree with K-fold cross-validation where K is equal to cv_folds.
  - Set Use1seRule flag to false (classifier.dt.r): If true, then a pruning will be harsher. This will make a tree more compact and more resistant to the training data noise but a bit less accurate.
  - Set TruncatePrunedTree flag to false (classifier.dt.t): If true, then pruned branches are physically removed from the tree.
- Gradient Boosted Tree classifier (gbt): This group of parameters allows setting Gradient Boosted Tree classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/gradient_boosted_trees.html}.
  - Number of boosting algorithm iterations (classifier.gbt.w): Number "w" of boosting algorithm iterations, with w*K being the total number of trees in the GBT model, where K is the output number of classes.
  - Regularization parameter (classifier.gbt.s): Regularization parameter.
  - Portion of the whole training set used for each algorithm iteration (classifier.gbt.p): Portion of the whole training set used for each algorithm iteration. The subset is generated randomly.
  - Maximum depth of the tree (classifier.gbt.max): The training algorithm attempts to split each node while its depth is smaller than the maximum possible depth of the tree. The actual depth may be smaller if the other termination criteria are met, and/or if the tree is pruned.
- Artificial Neural Network classifier (ann): This group of parameters allows setting Artificial Neural Network classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/neural_networks.html}.
  - Train Method Type (classifier.ann.t): Type of training method for the multilayer perceptron (MLP) neural network.
    - Back-propagation algorithm (back): Method to compute the gradient of the loss function and adjust weights in the network to optimize the result.
    - Resilient Back-propagation algorithm (reg): Almost the same as the Back-prop algorithm except that it does not take into account the magnitude of the partial derivative (coordinate of the gradient) but only its sign.
  - Number of neurons in each intermediate layer (classifier.ann.sizes): The number of neurons in each intermediate layer (excluding input and output layers).
  - Neuron activation function type (classifier.ann.f): This function determine whether the output of the node is positive or not depending on the output of the transfert function.
    - Identity function (ident):
    - Symmetrical Sigmoid function (sig):
    - Gaussian function (Not completely supported) (gau):
  - Alpha parameter of the activation function (classifier.ann.a): Alpha parameter of the activation function (used only with sigmoid and gaussian functions).
  - Beta parameter of the activation function (classifier.ann.b): Beta parameter of the activation function (used only with sigmoid and gaussian functions).
  - Strength of the weight gradient term in the BACKPROP method (classifier.ann.bpdw): Strength of the weight gradient term in the BACKPROP method. The recommended value is about 0.1.
  - Strength of the momentum term (the difference between weights on the 2 previous iterations) (classifier.ann.bpms): Strength of the momentum term (the difference between weights on the 2 previous iterations). This parameter provides some inertia to smooth the random fluctuations of the weights. It can vary from 0 (the feature is disabled) to 1 and beyond. The value 0.1 or so is good enough.
  - Initial value Delta_0 of update-values Delta_{ij} in RPROP method (classifier.ann.rdw): Initial value Delta_0 of update-values Delta_{ij} in RPROP method (default = 0.1).
  - Update-values lower limit Delta_{min} in RPROP method (classifier.ann.rdwm): Update-values lower limit Delta_{min} in RPROP method. It must be positive (default = 1e-7).
  - Termination criteria (classifier.ann.term): Termination criteria.
    - Maximum number of iterations (iter): Set the number of iterations allowed to the network for its training. Training will stop regardless of the result when this number is reached
    - Epsilon (eps): Training will focus on result and will stop once the precision isat most epsilon
    - Max. iterations + Epsilon (all): Both termination criteria are used. Training stop at the first reached
  - Epsilon value used in the Termination criteria (classifier.ann.eps): Epsilon value used in the Termination criteria.
  - Maximum number of iterations used in the Termination criteria (classifier.ann.iter): Maximum number of iterations used in the Termination criteria.
- Normal Bayes classifier (bayes): Use a Normal Bayes Classifier. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/normal_bayes_classifier.html}.
- Random forests classifier (rf): This group of parameters allows setting Random Forests classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/random_trees.html}.
  - Maximum depth of the tree (classifier.rf.max): The depth of the tree. A low value will likely underfit and conversely a high value will likely overfit. The optimal value can be obtained using cross validation or other suitable methods.
  - Minimum number of samples in each node (classifier.rf.min): If the number of samples in a node is smaller than this parameter, then the node will not be split. A reasonable value is a small percentage of the total data e.g. 1 percent.
  - Termination Criteria for regression tree (classifier.rf.ra): If all absolute differences between an estimated value in a node and the values of the train samples in this node are smaller than this regression accuracy parameter, then the node will not be split.
  - Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split (classifier.rf.cat): Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split.
  - Size of the randomly selected subset of features at each tree node (classifier.rf.var): The size of the subset of features, randomly selected at each tree node, that are used to find the best split(s). If you set it to 0, then the size will be set to the square root of the total number of features.
  - Maximum number of trees in the forest (classifier.rf.nbtrees): The maximum number of trees in the forest. Typically, the more trees you have, the better the accuracy. However, the improvement in accuracy generally diminishes and reaches an asymptote for a certain number of trees. Also to keep in mind, increasing the number of trees increases the prediction time linearly.
  - Sufficient accuracy (OOB error) (classifier.rf.acc): Sufficient accuracy (OOB error).
- KNN classifier (knn): This group of parameters allows setting KNN classifier parameters. See complete documentation here \url{http://docs.opencv.org/modules/ml/doc/k_nearest_neighbors.html}.
  - Number of Neighbors (classifier.knn.k): The number of neighbors to use.
- Shark Random forests classifier (sharkrf): This group of parameters allows setting Shark Random Forests classifier parameters. See complete documentation here \url{http://image.diku.dk/shark/doxygen_pages/html/classshark_1_1_r_f_trainer.html}.
  It is noteworthy that training is parallel.
  - Maximum number of trees in the forest (classifier.sharkrf.nbtrees): The maximum number of trees in the forest. Typically, the more trees you have, the better the accuracy. However, the improvement in accuracy generally diminishes and reaches an asymptote for a certain number of trees. Also to keep in mind, increasing the number of trees increases the prediction time linearly.
  - Min size of the node for a split (classifier.sharkrf.nodesize): If the number of samples in a node is smaller than this parameter, then the node will not be split. A reasonable value is a small percentage of the total data e.g. 1 percent.
  - Number of features tested at each node (classifier.sharkrf.mtry): The number of features (variables) which will be tested at each node in order to compute the split. If set to zero, the square root of the number of features is used.
  - Out of bound ratio (classifier.sharkrf.oobr): Set the fraction of the original training dataset to use as the out of bag sample.A good default value is 0.66.
- Shark kmeans classifier (sharkkm): This group of parameters allows setting Shark kMeans classifier parameters. See complete documentation here \url{http://image.diku.dk/shark/sphinx_pages/build/html/rest_sources/tutorials/algorithms/kmeans.html}.
  - Maximum number of iteration for the kmeans algorithm. (classifier.sharkkm.maxiter): The maximum number of iteration for the kmeans algorithm. 0=unlimited
  - The number of class used for the kmeans algorithm. (classifier.sharkkm.k): The number of class used for the kmeans algorithm. Default set to 2 class

set user defined seed (rand): Set specific seed. with integer value.
Load otb application from xml file (inxml): Load otb application from xml file
Save otb application to xml file (outxml): Save otb application to xml file

Limitations

Authors

OTB Team