classify_image_class_knnT_classify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn分类图像类K-最近邻（算子）

名称

classify_image_class_knnT_classify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn — 使用 k-最近邻分类器对图像进行分类。

签名

classify_image_class_knn(Image : ClassRegions, DistanceImage : KNNHandle, RejectionThreshold : )

描述

classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn 使用基于 k-最近邻（k-NN）分类器 KNNHandleKNNHandleKNNHandleKNNHandleKNNHandleknnhandle 对多通道图像 ImageImageImageImageimageimage 执行像素分类。在调用 classify_image_class_knnclassify_image_class_knnClassifyImageClassKnnClassifyImageClassKnnClassifyImageClassKnnclassify_image_class_knn 之前，必须使用 train_class_knntrain_class_knnTrainClassKnnTrainClassKnnTrainClassKnntrain_class_knn 对 k-NN 分类器进行训练。图像 ImageImageImageImageimageimage 必须具有 create_class_knncreate_class_knnCreateClassKnnCreateClassKnnCreateClassKnncreate_class_knn 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 中返回的区域顺序与 add_samples_image_class_knnadd_samples_image_class_knnAddSamplesImageClassKnnAddSamplesImageClassKnnAddSamplesImageClassKnnadd_samples_image_class_knn 中训练区域定义的类顺序相对应。参数 RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 可用于剔除分类结果不确定的像素。RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 表示分类返回的最近邻距离的阈值。所有概率低于 RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold 的像素均不被分配至任何类别。DistanceImageDistanceImageDistanceImageDistanceImagedistanceImagedistance_image 包含每个像素与其最近邻像素之间的距离。

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

ImageImageImageImageimageimage (输入对象) (multichannel-)image → object (byte / cyclic / direction / int1 / int2 / uint2 / int4 / real)

输入图像。

ClassRegionsClassRegionsClassRegionsClassRegionsclassRegionsclass_regions (输出对象) region-array → object (real)

分割的类别。

DistanceImageDistanceImageDistanceImageDistanceImagedistanceImagedistance_image (输出对象) image → object

像素最近邻的距离。

KNNHandleKNNHandleKNNHandleKNNHandleKNNHandleknnhandle (输入控制) class_knn → (handle)

k-NN 分类器的句柄。

RejectionThresholdRejectionThresholdRejectionThresholdRejectionThresholdrejectionThresholdrejection_threshold (输入控制) real → (real)

分类拒绝的阈值。

默认值： 0.5

建议值： 0.0, 0.1, 0.2, 0.3, 5.0, 10.0, 255.0

限制： RejectionThreshold >= 0.0

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_knn (3, KNNHandle)
add_samples_image_class_knn (Image, Classes, KNNHandle)
get_sample_num_class_knn (KNNHandle, NumSamples)
train_class_knn (KNNHandle, [], [])
classify_image_class_knn (Image, ClassRegions, DistanceImage, \
                          KNNHandle, 0.5)
dev_display (ClassRegions)

结果

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

可能的前趋

train_class_knntrain_class_knnTrainClassKnnTrainClassKnnTrainClassKnntrain_class_knn, read_class_knnread_class_knnReadClassKnnReadClassKnnReadClassKnnread_class_knn

替代

另见

add_samples_image_class_knnadd_samples_image_class_knnAddSamplesImageClassKnnAddSamplesImageClassKnnAddSamplesImageClassKnnadd_samples_image_class_knn, create_class_knncreate_class_knnCreateClassKnnCreateClassKnnCreateClassKnncreate_class_knn

模块

基础

算子