traind_ocr_class_boxT_traind_ocr_class_boxTraindOcrClassBoxTraindOcrClassBoxtraind_ocr_class_box (Operator)

Name

traind_ocr_class_boxT_traind_ocr_class_boxTraindOcrClassBoxTraindOcrClassBoxtraind_ocr_class_box — Train an OCR classifier by the input of regions.

Warning

traind_ocr_class_boxtraind_ocr_class_boxTraindOcrClassBoxTraindOcrClassBoxTraindOcrClassBoxtraind_ocr_class_box is obsolete and is only provided for reasons of backward compatibility. New applications should use the MLP, SVM or CNN based operators instead.

Signature

traind_ocr_class_box(Character, Image : : OcrHandle, Class : AvgConfidence)

Description

The operator traind_ocr_class_boxtraind_ocr_class_boxTraindOcrClassBoxTraindOcrClassBoxTraindOcrClassBoxtraind_ocr_class_box trains the classifier directly via the input of regions in an image. Any number of regions of an image can be passed. For each character (region) in CharacterCharacterCharacterCharactercharactercharacter the corresponding name (class) ClassClassClassClassclassValclass must be specified. The gray values are passed in ImageImageImageImageimageimage. When the procedure has finished the parameter AvgConfidenceAvgConfidenceAvgConfidenceAvgConfidenceavgConfidenceavg_confidence provides information about the success of the training: It contains the average confidence of the trained characters measured by a re-classification. The confidence of mismatched characters is set to 0 (thus, the average confidence will be decreased significantly).

Execution Information

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

This operator modifies the state of the following input parameter:

OcrHandleOcrHandleOcrHandleOcrHandleocrHandleocr_handle

During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.

Parameters

CharacterCharacterCharacterCharactercharactercharacter (input_object) region(-array) → object

Characters to be trained.

ImageImageImageImageimageimage (input_object) singlechannelimage → object (byte / uint2)

Gray values for the characters.

OcrHandleOcrHandleOcrHandleOcrHandleocrHandleocr_handle (input_control, state is modified) ocr_box → (handle)

ID of the desired OCR-classifier.

ClassClassClassClassclassValclass (input_control) string(-array) → (string)

Class (name) of the characters.

Default: 'a' "a" "a" "a" "a" "a"

AvgConfidenceAvgConfidenceAvgConfidenceAvgConfidenceavgConfidenceavg_confidence (output_control) real → (real)

Average confidence during a re-classification of the trained characters.

Example (C)

char name[128];
Hlong orc_handle;

read_ocr("testnet",&orc_handle);
read_image(&Image,"character.tiff");
binary_threshold(Image,&Dark, 'otsu', 'dark', &UsedThreshold);
connection(Dark,&Character);
count_obj(Character,&num);
open_window(0,0,-1,-1,0,"","",&WindowHandle);
set_color(WindowHandle,"red");
for (i=0; i<num; i++) {
  select_obj(Character,&SingleCharacter,i);
  disp_region(SingleCharacter,WindowHandle);
  printf("class of character %d ?\n",i);
  scanf("%s\n",name);
  traind_ocr_class_box(SingleCharacter,Image,OcrHandle,name,&AvgConfidence);
}

Result

If the parameters are correct, the operator traind_ocr_class_boxtraind_ocr_class_boxTraindOcrClassBoxTraindOcrClassBoxTraindOcrClassBoxtraind_ocr_class_box returns the value 2 ( H_MSG_TRUE) . Otherwise an exception will be raised.

Possible Predecessors

create_ocr_class_boxcreate_ocr_class_boxCreateOcrClassBoxCreateOcrClassBoxCreateOcrClassBoxcreate_ocr_class_box, read_ocrread_ocrReadOcrReadOcrReadOcrread_ocr

Possible Successors

write_ocrwrite_ocrWriteOcrWriteOcrWriteOcrwrite_ocr, do_ocr_multido_ocr_multiDoOcrMultiDoOcrMultiDoOcrMultido_ocr_multi, do_ocr_singledo_ocr_singleDoOcrSingleDoOcrSingleDoOcrSingledo_ocr_single

Alternatives

trainf_ocr_class_boxtrainf_ocr_class_boxTrainfOcrClassBoxTrainfOcrClassBoxTrainfOcrClassBoxtrainf_ocr_class_box

Module

OCR/OCV

Operators