Class TextRecognitionModel

Namespace

OpenCvSharp.Dnn

Assembly

OpenCvSharp.dll

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.

public class TextRecognitionModel : Model, IDisposable

Inheritance

object

CvObject

Model

TextRecognitionModel

Implements

IDisposable

Inherited Members

Model.SetHandle(nint, Func<nint, ExceptionStatus>)

Model.SetInputSize(Size)

Model.SetInputSize(int, int)

Model.SetInputMean(Scalar)

Model.SetInputScale(Scalar)

Model.SetInputCrop(bool)

Model.SetInputSwapRB(bool)

Model.SetOutputNames(IEnumerable<string>)

Model.SetInputParams(double, Size?, Scalar?, bool, bool)

Model.Predict(InputArray)

Model.SetPreferableBackend(Backend)

Model.SetPreferableTarget(Target)

Model.EnableWinograd(bool)

CvObject.IsDisposed

CvObject.ptr

CvObject.SetSafeHandle(OpenCvSafeHandle)

CvObject.Dispose()

CvObject.Dispose(bool)

CvObject.DisposeManaged()

CvObject.DisposeUnmanaged()

CvObject.ThrowIfDisposed()

CvObject.CvPtr

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

TextRecognitionModel(Net)

Create model from deep learning network.

public TextRecognitionModel(Net network)

Parameters

network Net

Net object.

TextRecognitionModel(string, string?)

Create text recognition model from network represented in one of the supported formats. An order of @p model and @p config arguments does not matter.

public TextRecognitionModel(string model, string? config = null)

Parameters

model string

Binary file contains trained weights.

config string

Text file contains network configuration.

Methods

GetDecodeType()

Get the decoding method.

public string GetDecodeType()

Returns

string

the decoding method

GetVocabulary()

Get the vocabulary for recognition.

public string?[] GetVocabulary()

Returns

string[]

vocabulary the associated vocabulary of the network.

Recognize(InputArray)

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

public string Recognize(InputArray frame)

Parameters

frame InputArray

The input image.

Returns

string

The text recognition result.

Recognize(InputArray, IEnumerable<Rect>)

Given the @p input frame, create input blob, run net and return recognition result for each ROI.

public string?[] Recognize(InputArray frame, IEnumerable<Rect> roiRects)

Parameters

frame InputArray

The input image.

roiRects IEnumerable<Rect>

List of text detection regions of interest. ROIs are cropped as the network inputs.

Returns

string[]

A set of text recognition results, one per ROI.

SetDecodeOptsCTCPrefixBeamSearch(int, int)

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

public void SetDecodeOptsCTCPrefixBeamSearch(int beamSize, int vocPruneSize = 0)

Parameters

beamSize int

Beam size for search

vocPruneSize int

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

SetDecodeType(string)

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

public void SetDecodeType(string decodeType)

Parameters

decodeType string

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(IEnumerable<string>)

Set the vocabulary for recognition.

public void SetVocabulary(IEnumerable<string> vocabulary)

Parameters

vocabulary IEnumerable<string>

the associated vocabulary of the network.