do_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knnT_do_ocr_single_class_knn🔗

Short description🔗

do_ocr_single_class_knnDoOcrSingleClassKnnDoOcrSingleClassKnndo_ocr_single_class_knnT_do_ocr_single_class_knn — Classify a single character with an OCR classifier.

Signature🔗

do_ocr_single_class_knn( region Character, image Image, ocr_knn OCRHandle, integer NumClasses, integer NumNeighbors, out string Class, out real Confidence )

Description🔗

do_ocr_single_class_knnDoOcrSingleClassKnn uses the OCR-k-NN classifier OCRHandleOCRHandleocrhandle to determine the best training samples for the features of the character given by the region Charactercharactercharacter and the gray values Imageimageimage and returns their classes in ClassclassValclass and the corresponding confidences in Confidenceconfidenceconfidence. If the first NumNeighborsnumNeighborsnum_neighbors training vectors have different classes, maximally NumClassesnumClassesnum_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 NumNeighborsnumNeighborsnum_neighbors is large enough.

Because multiple classes may be returned by do_ocr_single_class_knnDoOcrSingleClassKnn, Charactercharactercharacter may only contain a single region (a single character). If multiple characters should be classified in a single call, do_ocr_multi_class_knnDoOcrMultiClassKnn must be used. Before calling do_ocr_single_class_knnDoOcrSingleClassKnn, the classifier must be trained with trainf_ocr_class_knnTrainfOcrClassKnn or select_feature_set_trainf_knnSelectFeatureSetTrainfKnn. If all NumNeighborsnumNeighborsnum_neighbors neighbors are of the same class, only one class is returned.

Execution information🔗

Execution information

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Processed without parallelization.

Parameters🔗

Charactercharactercharacter (input_object) region → objectHObjectHRegionHObjectHobject

Character to be recognized.

Imageimageimage (input_object) singlechannelimage → object (byte / uint2)HObject (byte / uint2)HImage (byte / uint2)HObject (byte / uint2)Hobject (byte / uint2)

Gray values of the character.

OCRHandleOCRHandleocrhandle (input_control) ocr_knn → (handle)HTuple (HHandle)HOCRKnn, HTuple (IntPtr)HHandleHtuple (handle)

Handle of the k-NN classifier.

NumClassesnumClassesnum_classes (input_control) integer-array → (integer)HTuple (Hlong)HTuple (int / long)Sequence[int]Htuple (Hlong)

Number of maximal classes to determine.

Default: 11
Suggested values: 1, 2, 3, 4, 51, 2, 3, 4, 5

NumNeighborsnumNeighborsnum_neighbors (input_control) integer-array → (integer)HTuple (Hlong)HTuple (int / long)Sequence[int]Htuple (Hlong)

Number of neighbors to consider.

Default: 11
Suggested values: 1, 2, 3, 4, 51, 2, 3, 4, 5

ClassclassValclass (output_control) string(-array) → (string)HTuple (HString)HTuple (string)Sequence[str]Htuple (char*)

Results of classifying the character with the k-NN.

Confidenceconfidenceconfidence (output_control) real(-array) → (real)HTuple (double)HTuple (double)Sequence[float]Htuple (double)

Confidence(s) of the class(es) of the character.

Result🔗

If the parameters are valid, the operator do_ocr_single_class_knnDoOcrSingleClassKnn returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.

Combinations with other operators🔗

Combinations

Possible predecessors

trainf_ocr_class_knnTrainfOcrClassKnn, read_ocr_class_knnReadOcrClassKnn

Alternatives

do_ocr_multi_class_knnDoOcrMultiClassKnn

Module🔗

OCR/OCV