Test an OCR classifier.
The operator testd_ocr_class_box tests the confidence with which a character belongs to a given class. Any number of regions of an image can be passed. For each character (region) in Character the corresponding name (class) Class must be specified. The gray values are passed in Image. When the operator has finished the parameter Confidence provides information about how sure a character belongs to the (arbitrary chosen) class.
|
Character (input_object) |
region(-array) -> object |
| Characters to be tested. | |
|
Image (input_object) |
image -> object : byte / uint2 |
| Gray values for the characters. | |
|
OcrHandle (input_control) |
ocr -> integer |
| ID of the desired OCR-classifier. | |
|
Class (input_control) |
string(-array) -> string |
| Class (name) of the characters. | |
| Default value: ''a'' | |
|
Confidence (output_control) |
real(-array) -> real |
| Confidence for the character to belong to the class. | |
If the parameters are correct, the operator testd_ocr_class_box returns the value 2 (H_MSG_TRUE). Otherwise an exception will be raised.
testd_ocr_class_box is reentrant and automatically parallelized (on tuple level).
read_ocr, trainf_ocr_class_box, traind_ocr_class_box
OCR/OCV
