org.bytedeco.opencv.opencv_dnn

Class TextRecognitionModel

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.opencv.opencv_dnn.Model

org.bytedeco.opencv.opencv_dnn.TextRecognitionModel

All Implemented Interfaces:

AutoCloseable

@Namespace(value="cv::dnn")
 @Properties(inherit=opencv_dnn.class)
public class TextRecognitionModel
extends Model

\brief This class represents high-level API for text recognition networks. TextRecognitionModel allows to set params for preprocessing input image. TextRecognitionModel creates net from file with trained weights and config, sets preprocessing input, runs forward pass and return recognition result. For TextRecognitionModel, CRNN-CTC is supported.

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.opencv.opencv_dnn.Model

Model.Impl

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
TextRecognitionModel()
TextRecognitionModel(BytePointer model)
TextRecognitionModel(BytePointer model, BytePointer config) \brief Create text recognition model from network represented in one of the supported formats Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method
TextRecognitionModel(long size) Native array allocator.
TextRecognitionModel(Net network) \brief Create Text Recognition model from deep learning network Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method
TextRecognitionModel(Pointer p) Pointer cast constructor.
TextRecognitionModel(String model)
TextRecognitionModel(String model, String config)

Method Summary

Modifier and Type	Method and Description
BytePointer	getDecodeType() \brief Get the decoding method
TextRecognitionModel	getPointer(long i)
StringVector	getVocabulary() \brief Get the vocabulary for recognition.
TextRecognitionModel	position(long position)
BytePointer	recognize(GpuMat frame)
void	recognize(GpuMat frame, GpuMatVector roiRects, StringVector results)
void	recognize(GpuMat frame, MatVector roiRects, StringVector results)
void	recognize(GpuMat frame, UMatVector roiRects, StringVector results)
BytePointer	recognize(Mat frame) \brief Given the \p input frame, create input blob, run net and return recognition result
void	recognize(Mat frame, GpuMatVector roiRects, StringVector results)
void	recognize(Mat frame, MatVector roiRects, StringVector results) \brief Given the \p input frame, create input blob, run net and return recognition result
void	recognize(Mat frame, UMatVector roiRects, StringVector results)
String	recognize(UMat frame)
void	recognize(UMat frame, GpuMatVector roiRects, StringVector results)
void	recognize(UMat frame, MatVector roiRects, StringVector results)
void	recognize(UMat frame, UMatVector roiRects, StringVector results)
TextRecognitionModel	setDecodeOptsCTCPrefixBeamSearch(int beamSize)
TextRecognitionModel	setDecodeOptsCTCPrefixBeamSearch(int beamSize, int vocPruneSize) \brief Set the decoding method options for "CTC-prefix-beam-search" decode usage
TextRecognitionModel	setDecodeType(BytePointer decodeType) \brief Set the decoding method of translating the network output into string
TextRecognitionModel	setDecodeType(String decodeType)
TextRecognitionModel	setVocabulary(StringVector vocabulary) \brief Set the vocabulary for recognition.

Methods inherited from class org.bytedeco.opencv.opencv_dnn.Model

asNet, getImpl, getImplRef, getNetwork_, predict, predict, predict, predict, predict, predict, predict, predict, predict, put, setInputCrop, setInputMean, setInputParams, setInputParams, setInputScale, setInputSize, setInputSize, setInputSwapRB, setPreferableBackend, setPreferableTarget

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

TextRecognitionModel

public TextRecognitionModel(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

TextRecognitionModel

public TextRecognitionModel(long size)

Native array allocator. Access with Pointer.position(long).

TextRecognitionModel

public TextRecognitionModel()

TextRecognitionModel

public TextRecognitionModel(@Const @ByRef
                            Net network)

\brief Create Text Recognition model from deep learning network Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method

Parameters:

network - [in] Net object

TextRecognitionModel

public TextRecognitionModel(@StdString
                            BytePointer model,
                            @StdString
                            BytePointer config)

\brief Create text recognition model from network represented in one of the supported formats Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method

Parameters:

model - [in] Binary file contains trained weights

config - [in] Text file contains network configuration

TextRecognitionModel

public TextRecognitionModel(@StdString
                            BytePointer model)

TextRecognitionModel

public TextRecognitionModel(@StdString
                            String model,
                            @StdString
                            String config)

TextRecognitionModel

public TextRecognitionModel(@StdString
                            String model)

Method Detail

position

public TextRecognitionModel position(long position)

Overrides:

position in class Model

getPointer

public TextRecognitionModel getPointer(long i)

Overrides:

getPointer in class Model

setDecodeType

@ByRef
public TextRecognitionModel setDecodeType(@StdString
                                                 BytePointer decodeType)

\brief Set the decoding method of translating the network output into string

Parameters:

decodeType - [in] The decoding method of translating the network output into string, currently supported type: - "CTC-greedy" greedy decoding for the output of CTC-based methods - "CTC-prefix-beam-search" Prefix beam search decoding for the output of CTC-based methods

setDecodeType

@ByRef
public TextRecognitionModel setDecodeType(@StdString
                                                 String decodeType)

getDecodeType

@StdString
public BytePointer getDecodeType()

\brief Get the decoding method

Returns:

the decoding method

setDecodeOptsCTCPrefixBeamSearch

@ByRef
public TextRecognitionModel setDecodeOptsCTCPrefixBeamSearch(int beamSize,
                                                                    int vocPruneSize)

\brief Set the decoding method options for "CTC-prefix-beam-search" decode usage

Parameters:

beamSize - [in] Beam size for search

vocPruneSize - [in] Parameter to optimize big vocabulary search, only take top \p vocPruneSize tokens in each search step, \p vocPruneSize <= 0 stands for disable this prune.

setDecodeOptsCTCPrefixBeamSearch

@ByRef
public TextRecognitionModel setDecodeOptsCTCPrefixBeamSearch(int beamSize)

setVocabulary

@ByRef
public TextRecognitionModel setVocabulary(@Const @ByRef
                                                 StringVector vocabulary)

\brief Set the vocabulary for recognition.

Parameters:

vocabulary - [in] the associated vocabulary of the network.

getVocabulary

@Const
 @ByRef
public StringVector getVocabulary()

\brief Get the vocabulary for recognition.

Returns:

vocabulary the associated vocabulary

recognize

@StdString
public BytePointer recognize(@ByVal
                                        Mat frame)

\brief Given the \p input frame, create input blob, run net and return recognition result

Parameters:

frame - [in] The input image

Returns:

The text recognition result

recognize

@StdString
public String recognize(@ByVal
                                   UMat frame)

recognize

@StdString
public BytePointer recognize(@ByVal
                                        GpuMat frame)

recognize

public void recognize(@ByVal
                      Mat frame,
                      @ByVal
                      MatVector roiRects,
                      @ByRef
                      StringVector results)

\brief Given the \p input frame, create input blob, run net and return recognition result

Parameters:

frame - [in] The input image

roiRects - [in] List of text detection regions of interest (cv::Rect, CV_32SC4). ROIs is be cropped as the network inputs

results - [out] A set of text recognition results.

recognize

public void recognize(@ByVal
                      Mat frame,
                      @ByVal
                      UMatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      Mat frame,
                      @ByVal
                      GpuMatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      UMat frame,
                      @ByVal
                      MatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      UMat frame,
                      @ByVal
                      UMatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      UMat frame,
                      @ByVal
                      GpuMatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      GpuMat frame,
                      @ByVal
                      MatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      GpuMat frame,
                      @ByVal
                      UMatVector roiRects,
                      @ByRef
                      StringVector results)

recognize

public void recognize(@ByVal
                      GpuMat frame,
                      @ByVal
                      GpuMatVector roiRects,
                      @ByRef
                      StringVector results)