de.unihalle.informatik.MiToBo.apps.scratchAssay

Class ScratchAssaySVMTrainer

java.lang.Object

de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.MiToBo.core.operator.MTBOperator

de.unihalle.informatik.MiToBo.apps.scratchAssay.ScratchAssaySVMTrainer

All Implemented Interfaces:

de.unihalle.informatik.Alida.datatypes.ALDConfigurationValidator, de.unihalle.informatik.Alida.operator.events.ALDOperatorExecutionProgressEventListener, EventListener

@ALDAOperator(genericExecutionMode=SWING,
              level=STANDARD,
              allowBatchMode=false,
              shortDescription="Training and cross validation of support vector machines for classifying scratch assays.")
public class ScratchAssaySVMTrainer
extends MTBOperator

class for training and cross validating a support vector machine for classification of scratch assay
images into images containing a scratch and those that don't

Author:

glass

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ScratchAssaySVMTrainer.KERNEL_TYPE
static class	ScratchAssaySVMTrainer.ScratchOrientation
static class	ScratchAssaySVMTrainer.ValidationMethod

Nested classes/interfaces inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

de.unihalle.informatik.Alida.operator.ALDOperator.HidingMode, de.unihalle.informatik.Alida.operator.ALDOperator.HistoryConstructionMode

Field Summary

Fields

Modifier and Type	Field and Description
private Integer	C
private Integer	degree
private Integer	entropyFilterSize
private String	error_msg
(package private) StringBuffer	falseFileNames
(package private) StringBuffer	falseNegativeFileNames
(package private) StringBuffer	falsePositiveFileNames
private int	fn
private int	fp
private Boolean	isHorizontal
private Integer	k
private Integer	maxIter
private ScratchAssaySVMTrainer.ValidationMethod	method
private libsvm.svm_model	model
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString	negDir
private ScratchAssaySVMTrainer.ScratchOrientation	orientation
(package private) String	outFile
private libsvm.svm_parameter	param
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString	posDir
private libsvm.svm_problem	prob
private Integer	sigma
private int	tn
private int	tp
private ScratchAssaySVMTrainer.KERNEL_TYPE	type
private Vector<libsvm.svm_node[]>	vx
private Vector<Double>	vy

Fields inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

completeDAG, name, operatorExecutionEventlistenerList, portHashAccess, verbose, versionProvider

Constructor Summary

Constructors

Constructor and Description
ScratchAssaySVMTrainer()
ScratchAssaySVMTrainer(String posDir, String negDir, int sigma, int entropyFilterSize, boolean isHorizontal, int maxIter)

Method Summary

Modifier and Type	Method and Description
private void	addFeatures(double label, double[] features) add the given patterns (feature arrays) together with their corresponding label to the existing patterns used to train the SVM
private double	classify(double[] features)
private void	extract(File[] samples, double label) segment the given images and extract their features for classification
private void	extract(Vector<File> samples, double label) segment the given images and extract their features for classification
String	getDocumentation()
private void	leaveOneOutCrossValidation() leave-one-out cross validation, i.e. iteratively one sample is taken as test sample whereas all others are used for training
private MTBTableModel	makeTable()
void	operate()
private MTBImage	readImage(String path)
private void	saveSVM() save resulting svm model file
void	setSVMParameters(libsvm.svm_parameter param)
private void	showDegreeTextbox()
private void	showKTextbox()
private void	stratifiedCrossValidation() stratified k-fold cross validation, i.e. training and test tests contain approximately the same proportions of positive and negative samples in every iteration
private int[]	test(Vector<File> samples, int label)
private void	train() the actual svm training

Methods inherited from class de.unihalle.informatik.MiToBo.core.operator.MTBOperator

readResolve

Methods inherited from class de.unihalle.informatik.Alida.operator.ALDOperator

addOperatorExecutionProgressEventListener, addParameter, addParameter, addParameterUnconditioned, fieldContained, fireOperatorExecutionProgressEvent, getALDPortHashAccessKey, getConstructionMode, getHidingMode, getInactiveParameterNames, getInInoutNames, getInInoutNames, getInNames, getInOutNames, getMissingRequiredInputs, getName, getNumParameters, getOutInoutNames, getOutNames, getParameter, getParameterDescriptor, getParameterDescriptorUnconditioned, getParameterNames, getParameterUnconditioned, getSupplementalNames, getVerbose, getVersion, handleOperatorExecutionProgressEvent, hasInOutParameters, hasParameter, isAnnotatedParameter, isConfigured, print, print, print, printInterface, printInterface, readHistory, reinitializeParameterDescriptors, removeOperatorExecutionProgressEventListener, removeParameter, runOp, runOp, runOp, setConstructionMode, setConstructionMode, setConstructionMode, setHidingMode, setName, setParameter, setParameterUnconditioned, setVerbose, toStringVerbose, unconfiguredItems, validate, validateCustom, validateGeneric, writeHistory, writeHistory, writeHistory

Methods inherited from class java.lang.Object

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

Field Detail

posDir

@Parameter(label="directory containing positive samples",
           required=true,
           direction=IN,
           supplemental=false,
           description="directory containing positive samples",
           mode=STANDARD,
           dataIOOrder=0)
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString posDir

negDir

@Parameter(label="directory containing negative samples",
           required=true,
           direction=IN,
           supplemental=false,
           description="directory containing negative samples",
           mode=STANDARD,
           dataIOOrder=1)
private de.unihalle.informatik.Alida.datatypes.ALDDirectoryString negDir

orientation

@Parameter(label="scratch orientation",
           required=true,
           direction=IN,
           supplemental=false,
           description="horizontally or vertically oriented scratch",
           mode=STANDARD,
           dataIOOrder=2)
private ScratchAssaySVMTrainer.ScratchOrientation orientation

sigma

@Parameter(label="\u03c3",
           required=true,
           direction=IN,
           supplemental=false,
           description="standard deviation of gauss filter",
           mode=STANDARD,
           dataIOOrder=3)
private Integer sigma

entropyFilterSize

@Parameter(label="entropy filter size",
           required=true,
           direction=IN,
           supplemental=false,
           description="size of entropy filter mask",
           mode=STANDARD,
           dataIOOrder=4)
private Integer entropyFilterSize

C

@Parameter(label="regularization parameter (C)",
           required=false,
           direction=IN,
           supplemental=false,
           description="regularization parameter",
           mode=STANDARD,
           dataIOOrder=5)
private Integer C

type

@Parameter(label="kernel type",
           required=false,
           direction=IN,
           supplemental=false,
           description="type of svm kernel",
           mode=STANDARD,
           dataIOOrder=6,
           callback="showDegreeTextbox",
           paramModificationMode=MODIFIES_INTERFACE)
private ScratchAssaySVMTrainer.KERNEL_TYPE type

degree

@Parameter(label="polynomial degree",
           required=false,
           direction=IN,
           supplemental=false,
           description="degree for polynomial svm kernel",
           mode=STANDARD,
           dataIOOrder=7)
private Integer degree

method

@Parameter(label="validation method",
           required=false,
           direction=IN,
           supplemental=false,
           description="validation method for x-validation",
           mode=STANDARD,
           dataIOOrder=8,
           callback="showKTextbox",
           paramModificationMode=MODIFIES_INTERFACE)
private ScratchAssaySVMTrainer.ValidationMethod method

k

@Parameter(label="k (for k-fold x-validation)",
           required=false,
           direction=IN,
           supplemental=false,
           description="k for k-fold cross validation",
           mode=STANDARD,
           dataIOOrder=9)
private Integer k

maxIter

@Parameter(label="maximum iterations",
           required=false,
           direction=IN,
           supplemental=false,
           description="maximum number of iterations of level set segmentation",
           mode=ADVANCED,
           dataIOOrder=10)
private Integer maxIter

param

private libsvm.svm_parameter param

prob

private libsvm.svm_problem prob

model

private libsvm.svm_model model

error_msg

private String error_msg

vy

private Vector<Double> vy

vx

private Vector<libsvm.svm_node[]> vx

fp

private int fp

fn

private int fn

tp

private int tp

tn

private int tn

falsePositiveFileNames

StringBuffer falsePositiveFileNames

falseNegativeFileNames

StringBuffer falseNegativeFileNames

falseFileNames

StringBuffer falseFileNames

isHorizontal

private Boolean isHorizontal

outFile

String outFile

Constructor Detail

ScratchAssaySVMTrainer

public ScratchAssaySVMTrainer()
                       throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

ScratchAssaySVMTrainer

public ScratchAssaySVMTrainer(String posDir,
                              String negDir,
                              int sigma,
                              int entropyFilterSize,
                              boolean isHorizontal,
                              int maxIter)
                       throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Parameters:

posDir - directory containing positive samples

negDir - directory containing negative samples

sigma - standard deviation of gauss filter

entropyFilterSize - size of entropy filter mask

isHorizontal - is scratch horizontally oriented (assumed to be vertically oriented else)

maxIter - maximum number of iterations for level set segmentation

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

Method Detail

operate

public void operate()
             throws de.unihalle.informatik.Alida.exceptions.ALDOperatorException,
                    de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

Specified by:

operate in class de.unihalle.informatik.Alida.operator.ALDOperator

Throws:

de.unihalle.informatik.Alida.exceptions.ALDOperatorException

de.unihalle.informatik.Alida.exceptions.ALDProcessingDAGException

extract

private void extract(File[] samples,
                     double label)

segment the given images and extract their features for classification

Parameters:

samples - array of filenames containing images

label - label of the input images

extract

private void extract(Vector<File> samples,
                     double label)

segment the given images and extract their features for classification

Parameters:

samples - vector of filenames containing images

label - label of the input images

train

private void train()

the actual svm training

saveSVM

private void saveSVM()

save resulting svm model file

readImage

private MTBImage readImage(String path)

Parameters:

path -

Returns:

image read from given path, if it is a valid image path

addFeatures

private void addFeatures(double label,
                         double[] features)

add the given patterns (feature arrays) together with their corresponding label to the existing patterns used to train the SVM

Parameters:

label - label for the givven features

features - array of feature values

setSVMParameters

public void setSVMParameters(libsvm.svm_parameter param)

Parameters:

param -

stratifiedCrossValidation

private void stratifiedCrossValidation()

stratified k-fold cross validation, i.e. training and test tests contain approximately the same proportions of positive and negative samples in every iteration

leaveOneOutCrossValidation

private void leaveOneOutCrossValidation()

leave-one-out cross validation, i.e. iteratively one sample is taken as test
sample whereas all others are used for training

test

private int[] test(Vector<File> samples,
                   int label)

Parameters:

samples - Vector of sample files

label - ground truth labels for the input images

Returns:

numbers of right and wrong classified images

classify

private double classify(double[] features)

Parameters:

features -

Returns:

predicted class label

makeTable

private MTBTableModel makeTable()

Returns:

table containing the cross validation results

showDegreeTextbox

private void showDegreeTextbox()

showKTextbox

private void showKTextbox()

getDocumentation

public String getDocumentation()

Overrides:

getDocumentation in class de.unihalle.informatik.Alida.operator.ALDOperator