|
|||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objecthhreco.recognition.HHRecognizer
This is a general purpose recognizer in which feature extractors and the classifier can be user-specified. By default, the magnitudes of Zernike's moments to the 8th order are used as features.
Field Summary | |
static double |
CX
|
static double |
CY
|
static double |
SIZE
|
Constructor Summary | |
HHRecognizer()
Create a recognizer that uses the default Zernike Moments feature extractor and the default SVM classifier. |
|
HHRecognizer(FeatureExtractor[] extractors)
Create a recognizer that uses the specified set of feature extractors and the default SVM classifier. |
|
HHRecognizer(FeatureExtractor[] extractors,
TrainableClassifier c)
Create a recognizer that uses the specified set of feature extractors and the classifier. |
|
HHRecognizer(TrainableClassifier c)
Create a recognizer that uses the default Zernike Moments feature extractor and the specified classifier. |
Method Summary | |
int |
addAndRetrain(MSTrainingModel model)
Add the given set of data to the existing training set and retrain the recognizer. |
int |
addAndRetrain(java.lang.String type,
TimedStroke[] strokes)
Add the given shape to the existing training set and retrain the recognizer. |
static FeatureExtractor[] |
defaultFeatureExtractors()
|
static FeatureSet |
extractFeatures(FeatureExtractor[] extractors,
TimedStroke[] strokes)
Extract features from the given set of strokes. |
static TimedStroke[] |
preprocess(TimedStroke[] s,
ApproximateStrokeFilter approxFilter,
InterpolateStrokeFilter interpFilter,
java.awt.geom.AffineTransform at)
This preprocessing routine normalizes the scaling and the translation of the given shape. |
RecognitionSet |
sessionCompleted(TimedStroke[] strokes)
Perform recognition on the given shape. |
RecognitionSet |
strokeCompleted(TimedStroke s)
Invoked when a stroke is completed. |
RecognitionSet |
strokeModified(TimedStroke s)
Invoked when a stroke has been modified, for example, points have been added to the stroke. |
RecognitionSet |
strokeStarted(TimedStroke s)
Invoked when a stroke starts. |
int |
train(MSTrainingModel model)
Extract features from the training examples and train the classifier with them. |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
public static double SIZE
public static double CX
public static double CY
Constructor Detail |
public HHRecognizer()
public HHRecognizer(FeatureExtractor[] extractors)
public HHRecognizer(TrainableClassifier c)
public HHRecognizer(FeatureExtractor[] extractors, TrainableClassifier c)
Method Detail |
public static FeatureExtractor[] defaultFeatureExtractors()
public int addAndRetrain(java.lang.String type, TimedStroke[] strokes)
public int addAndRetrain(MSTrainingModel model)
public int train(MSTrainingModel model)
public static FeatureSet extractFeatures(FeatureExtractor[] extractors, TimedStroke[] strokes)
public RecognitionSet strokeStarted(TimedStroke s)
StrokeRecognizer
strokeStarted
in interface StrokeRecognizer
public RecognitionSet strokeModified(TimedStroke s)
StrokeRecognizer
strokeModified
in interface StrokeRecognizer
public RecognitionSet strokeCompleted(TimedStroke s)
StrokeRecognizer
strokeCompleted
in interface StrokeRecognizer
public RecognitionSet sessionCompleted(TimedStroke[] strokes)
sessionCompleted
in interface MultiStrokeRecognizer
public static TimedStroke[] preprocess(TimedStroke[] s, ApproximateStrokeFilter approxFilter, InterpolateStrokeFilter interpFilter, java.awt.geom.AffineTransform at)
|
|||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |