Package 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.
-
-
Constructor Summary
Constructors Modifier Constructor Description protected
TextRecognitionModel(long addr)
TextRecognitionModel(java.lang.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 methodTextRecognitionModel(java.lang.String model, java.lang.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 methodTextRecognitionModel(Net network)
Create Text Recognition model from deep learning network Call setDecodeType() and setVocabulary() after constructor to initialize the decoding method
-
Method Summary
All Methods Static Methods Instance Methods Concrete Methods Modifier and Type Method Description static TextRecognitionModel
__fromPtr__(long addr)
protected void
finalize()
java.lang.String
getDecodeType()
Get the decoding methodjava.util.List<java.lang.String>
getVocabulary()
Get the vocabulary for recognition.java.lang.String
recognize(Mat frame)
Given theinput
frame, create input blob, run net and return recognition resultvoid
recognize(Mat frame, java.util.List<Mat> roiRects, java.util.List<java.lang.String> results)
Given theinput
frame, create input blob, run net and return recognition resultTextRecognitionModel
setDecodeOptsCTCPrefixBeamSearch(int beamSize)
Set the decoding method options for"CTC-prefix-beam-search"
decode usageTextRecognitionModel
setDecodeOptsCTCPrefixBeamSearch(int beamSize, int vocPruneSize)
Set the decoding method options for"CTC-prefix-beam-search"
decode usageTextRecognitionModel
setDecodeType(java.lang.String decodeType)
Set the decoding method of translating the network output into stringTextRecognitionModel
setVocabulary(java.util.List<java.lang.String> vocabulary)
Set the vocabulary for recognition.-
Methods inherited from class org.opencv.dnn.Model
enableWinograd, getNativeObjAddr, predict, setInputCrop, setInputMean, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputScale, setInputSize, setInputSize, setInputSwapRB, setOutputNames, setPreferableBackend, setPreferableTarget
-
-
-
-
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(java.lang.String model, java.lang.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 weightsconfig
- Text file contains network configuration
-
TextRecognitionModel
public TextRecognitionModel(java.lang.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(java.lang.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 java.lang.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 searchvocPruneSize
- Parameter to optimize big vocabulary search, only take topvocPruneSize
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 topvocPruneSize
tokens in each search step,vocPruneSize
<= 0 stands for disable this prune.- Returns:
- automatically generated
-
setVocabulary
public TextRecognitionModel setVocabulary(java.util.List<java.lang.String> vocabulary)
Set the vocabulary for recognition.- Parameters:
vocabulary
- the associated vocabulary of the network.- Returns:
- automatically generated
-
getVocabulary
public java.util.List<java.lang.String> getVocabulary()
Get the vocabulary for recognition.- Returns:
- vocabulary the associated vocabulary
-
recognize
public java.lang.String recognize(Mat frame)
Given theinput
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, java.util.List<Mat> roiRects, java.util.List<java.lang.String> results)
Given theinput
frame, create input blob, run net and return recognition result- Parameters:
frame
- The input imageroiRects
- List of text detection regions of interest (cv::Rect, CV_32SC4). ROIs is be cropped as the network inputsresults
- A set of text recognition results.
-
-