classify_image_class_lutT_classify_image_class_lutClassifyImageClassLutClassifyImageClassLutclassify_image_class_lut (Operator)

Name

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

Signatur

Beschreibung

classify_image_class_lutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLutClassifyImageClassLutclassify_image_class_lut führt auf einem mehrkanaligen Byte-Bild ImageImageImageImageimageimage eine Pixelklassifikation anhand einer Look-Up-Table (LUT) ClassLUTHandleClassLUTHandleClassLUTHandleClassLUTHandleclassLUTHandleclass_luthandle durch. Der Operator kann classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm, classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn, classify_image_class_mlpclassify_image_class_mlpClassifyImageClassMlpClassifyImageClassMlpClassifyImageClassMlpclassify_image_class_mlp und classify_image_class_svmclassify_image_class_svmClassifyImageClassSvmClassifyImageClassSvmClassifyImageClassSvmclassify_image_class_svm 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_lutClassifyImageClassLutClassifyImageClassLutClassifyImageClassLutclassify_image_class_lut durch den entsprechend trainierten Klassifikator mit create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmmCreateClassLutGmmcreate_class_lut_gmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnnCreateClassLutKnncreate_class_lut_knn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlpCreateClassLutMlpcreate_class_lut_mlp bzw. create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvmCreateClassLutSvmcreate_class_lut_svm erzeugt werden. Für die Klassifizierung sind die in create_class_gmmcreate_class_gmmCreateClassGmmCreateClassGmmCreateClassGmmcreate_class_gmm, create_class_knncreate_class_knnCreateClassKnnCreateClassKnnCreateClassKnncreate_class_knn, create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpCreateClassMlpcreate_class_mlp bzw. create_class_svmcreate_class_svmCreateClassSvmCreateClassSvmCreateClassSvmcreate_class_svm 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 ClassRegionsClassRegionsClassRegionsClassRegionsclassRegionsclass_regions NumOutput bzw. NumClasses Regionen als Ergebnis der Pixelklassifikation zurückgegeben.

Ausführungsinformationen

• 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)
*
* classify the image with the LUT
classify_image_class_lut (Image, ClassRegions, ClassLUTHandle)

Ergebnis

Sind die Parameterwerte korrekt, dann liefert classify_image_class_lutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLutClassifyImageClassLutclassify_image_class_lut den Wert TRUE. Gegebenenfalls wird eine Fehlerbehandlung durchgeführt.

Vorgänger

create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmmCreateClassLutGmmcreate_class_lut_gmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnnCreateClassLutKnncreate_class_lut_knn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlpCreateClassLutMlpcreate_class_lut_mlp, create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvmCreateClassLutSvmcreate_class_lut_svm

Alternativen

classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm, classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn, classify_image_class_mlpclassify_image_class_mlpClassifyImageClassMlpClassifyImageClassMlpClassifyImageClassMlpclassify_image_class_mlp, classify_image_class_svmclassify_image_class_svmClassifyImageClassSvmClassifyImageClassSvmClassifyImageClassSvmclassify_image_class_svm

Siehe auch

create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmmCreateClassLutGmmcreate_class_lut_gmm, create_class_lut_knncreate_class_lut_knnCreateClassLutKnnCreateClassLutKnnCreateClassLutKnncreate_class_lut_knn, create_class_lut_mlpcreate_class_lut_mlpCreateClassLutMlpCreateClassLutMlpCreateClassLutMlpcreate_class_lut_mlp, create_class_lut_svmcreate_class_lut_svmCreateClassLutSvmCreateClassLutSvmCreateClassLutSvmcreate_class_lut_svm, create_class_lut_gmmcreate_class_lut_gmmCreateClassLutGmmCreateClassLutGmmCreateClassLutGmmcreate_class_lut_gmm

Modul

Foundation