get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn (算子)
名称
get_features_ocr_class_knnT_get_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn — 计算字符的特征。
签名
描述
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn computes the features of the
character given by CharacterCharacterCharacterCharactercharactercharacter with the k-NN classifier
OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle and returns them in FeaturesFeaturesFeaturesFeaturesfeaturesfeatures. In
contrast to do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn and
do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnnDoOcrMultiClassKnndo_ocr_multi_class_knn, the character is passed as a single
image object. Hence, before calling
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn, reduce_domainreduce_domainReduceDomainReduceDomainReduceDomainreduce_domain must
typically be called. The parameter TransformTransformTransformTransformtransformtransform determines
whether the feature transformation specified with
PreprocessingPreprocessingPreprocessingPreprocessingpreprocessingpreprocessing in create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnnCreateOcrClassKnncreate_ocr_class_knn for the
classifier should be applied (TransformTransformTransformTransformtransformtransform =
'true'"true""true""true""true""true") or whether the untransformed features should be
returned (TransformTransformTransformTransformtransformtransform = 'false'"false""false""false""false""false").
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn can be used to inspect the
features that are used for the classification.
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）。
- 未采用并行化处理。
参数
CharacterCharacterCharacterCharactercharactercharacter (输入对象) singlechannelimage → objectHImageHObjectHImageHobject (byte / uint2)
Input character.
OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle (输入控制) ocr_knn → HOCRKnn, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)
k-NN 分类器的句柄。
TransformTransformTransformTransformtransformtransform (输入控制) string → HTuplestrHTupleHtuple (string) (string) (HString) (char*)
Should the feature vector be transformed with
the preprocessing?
默认值：
'true'
"true"
"true"
"true"
"true"
"true"
值列表：
'false'"false""false""false""false""false", 'true'"true""true""true""true""true"
FeaturesFeaturesFeaturesFeaturesfeaturesfeatures (输出控制) real-array → HTupleSequence[float]HTupleHtuple (real) (double) (double) (double)
Feature vector of the character.
结果
如果参数有效，算子
get_features_ocr_class_knnget_features_ocr_class_knnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnGetFeaturesOcrClassKnnget_features_ocr_class_knn 返回值 2 ( H_MSG_TRUE )。如有必要，则抛出异常。
可能的前趋
trainf_ocr_class_knntrainf_ocr_class_knnTrainfOcrClassKnnTrainfOcrClassKnnTrainfOcrClassKnntrainf_ocr_class_knn
另见
create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnnCreateOcrClassKnncreate_ocr_class_knn
模块
光学字符识别/光学字符验证