Classify a single character with an OCR classifier.
do_ocr_single_class_mlp computes the best Num classes of the character given by the region Character and the gray values Image with the OCR classifier OCRHandle and returns the classes in Class and the corresponding confidences (probabilities) of the classes in Confidence. Because multiple classes may be returned by do_ocr_single_class_mlp, Character may only contain a single region (a single character). If multiple characters should be classified in a single call, do_ocr_multi_class_mlp must be used. Because do_ocr_multi_class_mlp typically is faster than a loop with do_ocr_single_class_mlp and because the confidences can be interpreted as probabilities (see classify_class_mlp and evaluate_class_mlp), and it is therefore easy to check whether a character has been classified with too much uncertainty, in most cases do_ocr_multi_class_mlp should be used, unless the second-best class should be examined explicitly. Before calling do_ocr_single_class_mlp, the classifier must be trained with trainf_ocr_class_mlp.
|
Character (input_object) |
region -> object |
| Character to be recognized. | |
|
Image (input_object) |
image -> object : byte / uint2 |
| Gray values of the character. | |
|
OCRHandle (input_control) |
ocr_mlp -> integer |
| Handle of the OCR classifier. | |
|
Num (input_control) |
real-array -> real |
| Number of best classes to determine. | |
| Default value: 1 | |
| Suggested values: 1, 2, 3, 4, 5 | |
|
Class (output_control) |
string(-array) -> string |
| Result of classifying the character with the MLP. | |
|
Confidence (output_control) |
real(-array) -> real |
| Confidence(s) of the class(es) of the character. | |
If the parameters are valid, the operator do_ocr_single_class_mlp returns the value 2 (H_MSG_TRUE). If necessary an exception handling is raised.
do_ocr_single_class_mlp is reentrant and processed without parallelization.
trainf_ocr_class_mlp, read_ocr_class_mlp
create_ocr_class_mlp, classify_class_mlp
OCR/OCV
