cv::dnn::TextRecognitionModel Class Reference

This class represents high-level API for text recognition networks. More...

#include <opencv2/dnn/dnn.hpp>

Collaboration diagram for cv::dnn::TextRecognitionModel:

Public Member Functions
	TextRecognitionModel ()
	TextRecognitionModel (const Net &network)
	Create Text Recognition model from deep learning network Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method.
	TextRecognitionModel (CV_WRAP_FILE_PATH const std::string &model, CV_WRAP_FILE_PATH const std::string &config="")
	Create text recognition model from network represented in one of the supported formats Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method.
const std::string &	getDecodeType () const
	Get the decoding method.
const std::vector< std::string > &	getVocabulary () const
	Get the vocabulary for recognition.
std::string	recognize (InputArray frame) const
	Given the input frame, create input blob, run net and return recognition result.
void	recognize (InputArray frame, InputArrayOfArrays roiRects, std::vector< std::string > &results) const
	Given the input frame, create input blob, run net and return recognition result.
TextRecognitionModel &	setDecodeOptsCTCPrefixBeamSearch (int beamSize, int vocPruneSize=0)
	Set the decoding method options for "CTC-prefix-beam-search" decode usage.
TextRecognitionModel &	setDecodeType (const std::string &decodeType)
	Set the decoding method of translating the network output into string.
TextRecognitionModel &	setVocabulary (const std::vector< std::string > &vocabulary)
	Set the vocabulary for recognition.
Public Member Functions inherited from cv::dnn::Model
	Model ()
	Model (const Model &)=default
	Model (const Net &network)
	Create model from deep learning network.
	Model (CV_WRAP_FILE_PATH const String &model, CV_WRAP_FILE_PATH const String &config="")
	Create model from deep learning network represented in one of the supported formats. An order of model and config arguments does not matter.
	Model (Model &&)=default
Model &	enableWinograd (bool useWinograd)
Impl *	getImpl () const
Impl &	getImplRef () const
Net &	getNetwork_ ()
Net &	getNetwork_ () const
	operator Net & () const
Model &	operator= (const Model &)=default
Model &	operator= (Model &&)=default
void	predict (InputArray frame, OutputArrayOfArrays outs) const
	Given the input frame, create input blob, run net and return the output blobs.
Model &	setInputCrop (bool crop)
	Set flag crop for frame.
Model &	setInputMean (const Scalar &mean)
	Set mean value for frame.
void	setInputParams (double scale=1.0, const Size &size=Size(), const Scalar &mean=Scalar(), bool swapRB=false, bool crop=false)
	Set preprocessing parameters for frame.
Model &	setInputScale (const Scalar &scale)
	Set scalefactor value for frame.
Model &	setInputSize (const Size &size)
	Set input size for frame.
Model &	setInputSize (int width, int height)
Model &	setInputSwapRB (bool swapRB)
	Set flag swapRB for frame.
Model &	setOutputNames (const std::vector< String > &outNames)
	Set output names for frame.
Model &	setPreferableBackend (dnn::Backend backendId)
Model &	setPreferableTarget (dnn::Target targetId)

Additional Inherited Members
Protected Attributes inherited from cv::dnn::Model
Ptr< Impl >	impl

Detailed Description

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.

Examples

samples/dnn/text_detection.cpp.

Constructor & Destructor Documentation

TextRecognitionModel() [1/3]

cv::dnn::TextRecognitionModel::TextRecognitionModel

(

)

Python:
	cv.dnn.TextRecognitionModel(	network	) ->	<dnn_TextRecognitionModel object>
	cv.dnn.TextRecognitionModel(	model[, config]	) ->	<dnn_TextRecognitionModel object>

TextRecognitionModel() [2/3]

cv::dnn::TextRecognitionModel::TextRecognitionModel

(

const Net &

network

)

Python:
	cv.dnn.TextRecognitionModel(	network	) ->	<dnn_TextRecognitionModel object>
	cv.dnn.TextRecognitionModel(	model[, config]	) ->	<dnn_TextRecognitionModel object>

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

Parameters

[in]

network

Net object

TextRecognitionModel() [3/3]

cv::dnn::TextRecognitionModel::TextRecognitionModel ( CV_WRAP_FILE_PATH const std::string &  model, CV_WRAP_FILE_PATH const std::string &  config = ""  )

inline

Python:
	cv.dnn.TextRecognitionModel(	network	) ->	<dnn_TextRecognitionModel object>
	cv.dnn.TextRecognitionModel(	model[, config]	) ->	<dnn_TextRecognitionModel object>

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

[in]	model	Binary file contains trained weights
[in]	config	Text file contains network configuration

Here is the call graph for this function:

Member Function Documentation

getDecodeType()

const std::string & cv::dnn::TextRecognitionModel::getDecodeType

(

)

const

Python:
	cv.dnn.TextRecognitionModel.getDecodeType(		) ->	retval

Get the decoding method.

Returns

the decoding method

getVocabulary()

const std::vector< std::string > & cv::dnn::TextRecognitionModel::getVocabulary

(

)

const

Python:
	cv.dnn.TextRecognitionModel.getVocabulary(		) ->	retval

Get the vocabulary for recognition.

Returns

vocabulary the associated vocabulary

recognize() [1/2]

std::string cv::dnn::TextRecognitionModel::recognize

(

InputArray

frame

)

const

Python:
	cv.dnn.TextRecognitionModel.recognize(	frame	) ->	retval
	cv.dnn.TextRecognitionModel.recognize(	frame, roiRects	) ->	results

Given the input frame, create input blob, run net and return recognition result.

Parameters

[in]

frame

The input image

Returns

The text recognition result

recognize() [2/2]

void cv::dnn::TextRecognitionModel::recognize	(	InputArray	frame,
		InputArrayOfArrays	roiRects,
		std::vector< std::string > &	results
	)		const

Python:
	cv.dnn.TextRecognitionModel.recognize(	frame	) ->	retval
	cv.dnn.TextRecognitionModel.recognize(	frame, roiRects	) ->	results

Given the input frame, create input blob, run net and return recognition result.

Parameters

[in]	frame	The input image
[in]	roiRects	List of text detection regions of interest (cv::Rect, CV_32SC4). ROIs is be cropped as the network inputs
[out]	results	A set of text recognition results.

setDecodeOptsCTCPrefixBeamSearch()

TextRecognitionModel & cv::dnn::TextRecognitionModel::setDecodeOptsCTCPrefixBeamSearch	(	int	beamSize,
		int	vocPruneSize = 0
	)

Python:
	cv.dnn.TextRecognitionModel.setDecodeOptsCTCPrefixBeamSearch(	beamSize[, vocPruneSize]	) ->	retval

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

Parameters

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

setDecodeType()

TextRecognitionModel & cv::dnn::TextRecognitionModel::setDecodeType

(

const std::string &

decodeType

)

Python:
	cv.dnn.TextRecognitionModel.setDecodeType(	decodeType	) ->	retval

Set the decoding method of translating the network output into string.

Parameters

[in]

decodeType

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

setVocabulary()

TextRecognitionModel & cv::dnn::TextRecognitionModel::setVocabulary

(

const std::vector< std::string > &

vocabulary

)

Python:
	cv.dnn.TextRecognitionModel.setVocabulary(	vocabulary	) ->	retval

Set the vocabulary for recognition.

Parameters

[in]

vocabulary

the associated vocabulary of the network.

---

The documentation for this class was generated from the following file:

• opencv2/dnn/dnn.hpp