do_ocr_single_class_knnT_do_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn (算子)

名称

do_ocr_single_class_knnT_do_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn — 使用 OCR 分类器对单个字符进行分类。

签名

描述

do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn uses the OCR-k-NN classifier OCRHandleOCRHandleOCRHandleOCRHandleOCRHandleocrhandle to determine the best training samples for the features of the character given by the region CharacterCharacterCharacterCharactercharactercharacter and the gray values ImageImageImageImageimageimage and returns their classes in ClassClassClassClassclassValclass and the corresponding confidences in ConfidenceConfidenceConfidenceConfidenceconfidenceconfidence. If the first NumNeighborsNumNeighborsNumNeighborsNumNeighborsnumNeighborsnum_neighbors training vectors have different classes, maximally NumClassesNumClassesNumClassesNumClassesnumClassesnum_classes classes are returned sorted by frequency and weighted distance. The confidences lie between 0.0 and 1.0. The larger the value, the more reliable is the classification. The confidence can be only computed robustly if NumNeighborsNumNeighborsNumNeighborsNumNeighborsnumNeighborsnum_neighbors is large enough.

Because multiple classes may be returned by do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn, CharacterCharacterCharacterCharactercharactercharacter may only contain a single region (a single character). If multiple characters should be classified in a single call, do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnnDoOcrMultiClassKnndo_ocr_multi_class_knn must be used. Before calling do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knn, the classifier must be trained with trainf_ocr_class_knntrainf_ocr_class_knnTrainfOcrClassKnnTrainfOcrClassKnnTrainfOcrClassKnntrainf_ocr_class_knn or select_feature_set_trainf_knnselect_feature_set_trainf_knnSelectFeatureSetTrainfKnnSelectFeatureSetTrainfKnnSelectFeatureSetTrainfKnnselect_feature_set_trainf_knn。If all NumNeighborsNumNeighborsNumNeighborsNumNeighborsnumNeighborsnum_neighbors neighbors are of the same class, only one class is returned.

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

结果

如果参数有效，算子 do_ocr_single_class_knndo_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_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, read_ocr_class_knnread_ocr_class_knnReadOcrClassKnnReadOcrClassKnnReadOcrClassKnnread_ocr_class_knn

替代

do_ocr_multi_class_knndo_ocr_multi_class_knnDoOcrMultiClassKnnDoOcrMultiClassKnnDoOcrMultiClassKnndo_ocr_multi_class_knn

另见

create_ocr_class_knncreate_ocr_class_knnCreateOcrClassKnnCreateOcrClassKnnCreateOcrClassKnncreate_ocr_class_knn, classify_class_knnclassify_class_knnClassifyClassKnnClassifyClassKnnClassifyClassKnnclassify_class_knn

模块

光学字符识别/光学字符验证