public static class opencv_text.OCRBeamSearchDecoder.ClassifierCallback extends Pointer
This way it hides the feature extractor and the classifier itself, so developers can write their own OCR code.
The default character classifier and feature extractor can be loaded using the utility funtion
loadOCRBeamSearchClassifierCNN with all its parameters provided in
Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator| Constructor and Description |
|---|
ClassifierCallback()
Default native constructor.
|
ClassifierCallback(long size)
Native array allocator.
|
ClassifierCallback(Pointer p)
Pointer cast constructor.
|
| Modifier and Type | Method and Description |
|---|---|
void |
eval(opencv_core.Mat image,
opencv_text.DoubleVector recognition_probabilities,
IntBuffer oversegmentation) |
void |
eval(opencv_core.Mat image,
opencv_text.DoubleVector recognition_probabilities,
IntPointer oversegmentation)
\brief The character classifier must return a (ranked list of) class(es) id('s)
|
void |
eval(opencv_core.UMat image,
opencv_text.DoubleVector recognition_probabilities,
int[] oversegmentation) |
void |
eval(opencv_core.UMat image,
opencv_text.DoubleVector recognition_probabilities,
IntPointer oversegmentation) |
int |
getStepSize() |
int |
getWindowSize() |
opencv_text.OCRBeamSearchDecoder.ClassifierCallback |
position(long position) |
address, asBuffer, asByteBuffer, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, free, hashCode, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetof, physicalBytes, position, put, realloc, setNull, sizeof, toString, totalBytes, withDeallocator, zeropublic ClassifierCallback()
public ClassifierCallback(long size)
Pointer.position(long).public ClassifierCallback(Pointer p)
Pointer.Pointer(Pointer).public opencv_text.OCRBeamSearchDecoder.ClassifierCallback position(long position)
public void eval(@ByVal opencv_core.Mat image, @StdVector opencv_text.DoubleVector recognition_probabilities, @StdVector IntPointer oversegmentation)
image - Input image CV_8UC1 or CV_8UC3 with a single letter.recognition_probabilities - For each of the N characters found the classifier returns a list with
class probabilities for each class.oversegmentation - The classifier returns a list of N+1 character locations' x-coordinates,
including 0 as start-sequence location.public void eval(@ByVal opencv_core.Mat image, @StdVector opencv_text.DoubleVector recognition_probabilities, @StdVector IntBuffer oversegmentation)
public void eval(@ByVal opencv_core.UMat image, @StdVector opencv_text.DoubleVector recognition_probabilities, @StdVector int[] oversegmentation)
public void eval(@ByVal opencv_core.UMat image, @StdVector opencv_text.DoubleVector recognition_probabilities, @StdVector IntPointer oversegmentation)
public int getWindowSize()
public int getStepSize()
Copyright © 2017. All rights reserved.