classify_image_class_gmmT_classify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm分类图像类高斯混合模型（算子）

名称

classify_image_class_gmmT_classify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm — 使用高斯混合模型对图像进行分类。

签名

描述

classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm 使用高斯混合模型（GMM）GMMHandleGMMHandleGMMHandleGMMHandleGMMHandlegmmhandle 对多通道图像 ImageImageImageImageimageimage 执行像素分类。在调用 classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm 之前，必须通过 train_class_gmmtrain_class_gmmTrainClassGmmTrainClassGmmTrainClassGmmtrain_class_gmm 对 GMM 进行训练。图像 ImageImageImageImageimageimage 必须具有 create_class_gmmcreate_class_gmmCreateClassGmmCreateClassGmmCreateClassGmmcreate_class_gmm 中指定的 NumDimNumDimNumDimNumDimnumDimnum_dim 个通道。输出时，ClassRegionsClassRegionsClassRegionsClassRegionsclassRegionsclass_regions 将包含 NumClassesNumClassesNumClassesNumClassesnumClassesnum_classes 个区域作为分类结果。请注意，ClassRegionsClassRegionsClassRegionsClassRegionsclassRegionsclass_regions 返回的区域顺序与 add_samples_image_class_gmmadd_samples_image_class_gmmAddSamplesImageClassGmmAddSamplesImageClassGmmAddSamplesImageClassGmmadd_samples_image_class_gmm 中训练区域定义的类别顺序一致。参数 RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 可用于剔除分类结果不确定的像素。RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 表示分类结果返回的 K-sigma 概率测度阈值（详见 classify_class_gmmclassify_class_gmmClassifyClassGmmClassifyClassGmmClassifyClassGmmclassify_class_gmm 和 evaluate_class_gmmevaluate_class_gmmEvaluateClassGmmEvaluateClassGmmEvaluateClassGmmevaluate_class_gmm）。所有概率低于 RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 的像素均不被分配至任何类别。

执行信息

• 多线程类型：可重入（与非独占算子并行运行）。
• 多线程作用域：全局（可从任何线程调用）。
• 在内部数据级别上自动并行化。

参数

示例（HDevelop）

read_image (Image, 'ic')
gen_rectangle1 (Board, 80, 320, 110, 350)
gen_rectangle1 (Capacitor, 359, 263, 371, 302)
gen_rectangle1 (Resistor, 200, 252, 290, 256)
gen_rectangle1 (IC, 180, 135, 216, 165)
concat_obj (Board, Capacitor, Classes)
concat_obj (Classes, Resistor, Classes)
concat_obj (Classes, IC, Classes)
create_class_gmm (3, 4, [1,30], 'full', 'none',0, 42, GMMHandle)
add_samples_image_class_gmm (Image, Classes, GMMHandle, 1.5)
get_sample_num_class_gmm (GMMHandle, NumSamples)
train_class_gmm (GMMHandle, 150, 1e-4, 'training', 1e-4, Centers, Iter)
classify_image_class_gmm (Image, ClassRegions, GMMHandle, 0.0001)

结果

如果参数有效，算子 classify_image_class_gmmclassify_image_class_gmmClassifyImageClassGmmClassifyImageClassGmmClassifyImageClassGmmclassify_image_class_gmm 返回值 2 (H_MSG_TRUE)。如有必要，则抛出异常。

可能的前趋

train_class_gmmtrain_class_gmmTrainClassGmmTrainClassGmmTrainClassGmmtrain_class_gmm, read_class_gmmread_class_gmmReadClassGmmReadClassGmmReadClassGmmread_class_gmm

替代

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, classify_image_class_lutclassify_image_class_lutClassifyImageClassLutClassifyImageClassLutClassifyImageClassLutclassify_image_class_lut, class_ndim_normclass_ndim_normClassNdimNormClassNdimNormClassNdimNormclass_ndim_norm, class_2dim_supclass_2dim_supClass2dimSupClass2dimSupClass2dimSupclass_2dim_sup

另见

add_samples_image_class_gmmadd_samples_image_class_gmmAddSamplesImageClassGmmAddSamplesImageClassGmmAddSamplesImageClassGmmadd_samples_image_class_gmm, create_class_gmmcreate_class_gmmCreateClassGmmCreateClassGmmCreateClassGmmcreate_class_gmm

模块

基础