org.opencv.dnn

Class TextRecognitionModel

java.lang.Object

org.opencv.dnn.Model

org.opencv.dnn.TextRecognitionModel

public class TextRecognitionModel
extends Model

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.

Field Summary

Fields inherited from class org.opencv.dnn.Model

nativeObj

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	TextRecognitionModel(long addr)
	TextRecognitionModel(Net network) Create Text Recognition model from deep learning network Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method
	TextRecognitionModel(String model) 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(String model, 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

Method Summary

Modifier and Type	Method and Description
static TextRecognitionModel	__fromPtr__(long addr)
protected void	finalize()
String	getDecodeType() Get the decoding method
List<String>	getVocabulary() Get the vocabulary for recognition.
String	recognize(Mat frame) Given the input frame, create input blob, run net and return recognition result
void	recognize(Mat frame, List<Mat> roiRects, List<String> results) Given the input frame, create input blob, run net and return recognition result
TextRecognitionModel	setDecodeOptsCTCPrefixBeamSearch(int beamSize) Set the decoding method options for "CTC-prefix-beam-search" decode usage
TextRecognitionModel	setDecodeOptsCTCPrefixBeamSearch(int beamSize, int vocPruneSize) Set the decoding method options for "CTC-prefix-beam-search" decode usage
TextRecognitionModel	setDecodeType(String decodeType) Set the decoding method of translating the network output into string
TextRecognitionModel	setVocabulary(List<String> vocabulary) Set the vocabulary for recognition.

Methods inherited from class org.opencv.dnn.Model

getNativeObjAddr, predict, setInputCrop, setInputMean, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputScale, setInputSize, setInputSize, setInputSwapRB, setPreferableBackend, setPreferableTarget

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

TextRecognitionModel

protected TextRecognitionModel(long addr)

TextRecognitionModel

public TextRecognitionModel(Net network)

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

Parameters:

network - Net object

TextRecognitionModel

public TextRecognitionModel(String model,
                            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

Parameters:

model - Binary file contains trained weights

config - Text file contains network configuration

TextRecognitionModel

public TextRecognitionModel(String model)

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 - Binary file contains trained weights

Method Detail

__fromPtr__

public static TextRecognitionModel __fromPtr__(long addr)

setDecodeType

public TextRecognitionModel setDecodeType(String decodeType)

Set the decoding method of translating the network output into string

Parameters:

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

Returns:

automatically generated

getDecodeType

public String getDecodeType()

Get the decoding method

Returns:

the decoding method

setDecodeOptsCTCPrefixBeamSearch

public TextRecognitionModel setDecodeOptsCTCPrefixBeamSearch(int beamSize,
                                                             int vocPruneSize)

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

Parameters:

beamSize - Beam size for search

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

Returns:

automatically generated

setDecodeOptsCTCPrefixBeamSearch

public TextRecognitionModel setDecodeOptsCTCPrefixBeamSearch(int beamSize)

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

Parameters:

beamSize - Beam size for search only take top vocPruneSize tokens in each search step, vocPruneSize <= 0 stands for disable this prune.

Returns:

automatically generated

setVocabulary

public TextRecognitionModel setVocabulary(List<String> vocabulary)

Set the vocabulary for recognition.

Parameters:

vocabulary - the associated vocabulary of the network.

Returns:

automatically generated

getVocabulary

public List<String> getVocabulary()

Get the vocabulary for recognition.

Returns:

vocabulary the associated vocabulary

recognize

public String recognize(Mat frame)

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

Parameters:

frame - The input image

Returns:

The text recognition result

recognize

public void recognize(Mat frame,
                      List<Mat> roiRects,
                      List<String> results)

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

Parameters:

frame - The input image

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

results - A set of text recognition results.

finalize

protected void finalize()
                 throws Throwable

Overrides:

finalize in class Model

Throws:

Throwable