classify_image_class_lutclassify_image_class_lutClassifyImageClassLutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLut (Operator)

Name

classify_image_class_lutclassify_image_class_lutClassifyImageClassLutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLut — Klassifizieren eines Byte-Bildes mit einer Look-Up-Table.

Signatur

Beschreibung

classify_image_class_lutclassify_image_class_lutClassifyImageClassLutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLut führt auf einem mehrkanaligen Byte-Bild ImageImageImageImageImageimage eine Pixelklassifikation anhand einer Look-Up-Table (LUT) ClassLUTHandleClassLUTHandleClassLUTHandleClassLUTHandleClassLUTHandleclassLUTHandle durch. Der Operator kann classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmm, classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnn, classify_image_class_mlpclassify_image_class_mlpClassifyImageClassMlpclassify_image_class_mlpClassifyImageClassMlpClassifyImageClassMlp und classify_image_class_svmclassify_image_class_svmClassifyImageClassSvmclassify_image_class_svmClassifyImageClassSvmClassifyImageClassSvm ersetzen, was die Klassifikation deutlich beschleunigt, weil die entsprechende Klasse nicht in jedem Bildpunkt extra berechnet werden muss, da alle möglichen Antworten des GMM, KNN, MLP bzw. SVM in der LUT gespeichert sind. Dieser LUT Klassifikator muss vor der Verwendung von classify_image_class_lutclassify_image_class_lutClassifyImageClassLutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLut durch den entsprechend trainierten Klassifikator mit create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlp bzw. create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvm erzeugt werden. Für die Klassifizierung sind die in create_class_gmmcreate_class_gmmCreateClassGmmcreate_class_gmmCreateClassGmmCreateClassGmm, create_class_knncreate_class_knnCreateClassKnncreate_class_knnCreateClassKnnCreateClassKnn, create_class_mlpcreate_class_mlpCreateClassMlpcreate_class_mlpCreateClassMlpCreateClassMlp bzw. create_class_svmcreate_class_svmCreateClassSvmcreate_class_svmCreateClassSvmCreateClassSvm angegeben Parameter von Bedeutung: Das Byte-Bild ImageImageImageImageImageimage muss die selbe Anzahl von Kanälen besitzen, wie in NumInput, NumFeatures bzw. NumDim spezifiziert wurde. Als Ausgabe werden in ClassRegionsClassRegionsClassRegionsClassRegionsClassRegionsclassRegions NumOutput bzw. NumClasses Regionen als Ergebnis der Pixelklassifikation zurückgegeben.

Parallelisierung

• Multithreading-Typ: reentrant (läuft parallel zu nicht-exklusiven Operatoren).
• Multithreading-Bereich: global (kann von jedem Thread aufgerufen werden).
• Automatisch parallelisiert auf interner Datenebene.

Parameter

Beispiel (HDevelop)

read_image (Image, 'patras')
gen_rectangle1 (Sea, 10, 10, 120, 270)
gen_rectangle2 (Deck, [170,400], [350,375], [-0.56192,-0.75139], \
                [64,104], [26,11])
union1 (Deck, Deck)
gen_rectangle1 (Walls, 355, 623, 420, 702)
gen_rectangle2 (Chimney, 286, 623, -0.56192, 64, 33)
concat_obj (Sea, Deck, Classes)
concat_obj (Classes, Walls, Classes)
concat_obj (Classes, Chimney, Classes)
*
* create MLP classifier and train it with sample classes
create_class_mlp (3, 3, 4, 'softmax', 'principal_components', 3, \
                  42, MLPHandle)
add_samples_image_class_mlp (Image, Classes, MLPHandle)
train_class_mlp (MLPHandle, 200, 1, 0.01, Error, ErrorLog)
*
* create the LUT classifier
create_class_lut_mlp (MLPHandle, [], [], ClassLUTHandle)
clear_class_mlp (MLPHandle)
*
* classify the image with the LUT
classify_image_class_lut (Image, ClassRegions, ClassLUTHandle)
clear_class_lut (ClassLUTHandle)

Ergebnis

Sind die Parameterwerte korrekt, dann liefert classify_image_class_lutclassify_image_class_lutClassifyImageClassLutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLut den Wert 2 (H_MSG_TRUE). Gegebenenfalls wird eine Fehlerbehandlung durchgeführt.

Vorgänger

create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlp, create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvm

Alternativen

classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmm, classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnn, classify_image_class_mlpclassify_image_class_mlpClassifyImageClassMlpclassify_image_class_mlpClassifyImageClassMlpClassifyImageClassMlp, classify_image_class_svmclassify_image_class_svmClassifyImageClassSvmclassify_image_class_svmClassifyImageClassSvmClassifyImageClassSvm

Siehe auch

create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlp, create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvm, create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmm

Modul

Foundation