OpenCV  4.0.0
Open Source Computer Vision
Public Member Functions | List of all members
cv::text::OCRBeamSearchDecoder::ClassifierCallback Class Reference

Callback with the character classifier is made a class. More...

#include "ocr.hpp"

Public Member Functions

virtual ~ClassifierCallback ()
 
virtual void eval (InputArray image, std::vector< std::vector< double > > &recognition_probabilities, std::vector< int > &oversegmentation)
 The character classifier must return a (ranked list of) class(es) id('s) More...
 
int getStepSize ()
 
int getWindowSize ()
 

Detailed Description

Callback with the character classifier is made a class.

This way it hides the feature extractor and the classifier itself, so developers can write their own OCR code.

The default character classifier and feature extractor can be loaded using the utility funtion loadOCRBeamSearchClassifierCNN with all its parameters provided in https://github.com/opencv/opencv_contrib/blob/master/modules/text/samples/OCRBeamSearch_CNN_model_data.xml.gz.

Constructor & Destructor Documentation

§ ~ClassifierCallback()

virtual cv::text::OCRBeamSearchDecoder::ClassifierCallback::~ClassifierCallback ( )
inlinevirtual

Member Function Documentation

§ eval()

virtual void cv::text::OCRBeamSearchDecoder::ClassifierCallback::eval ( InputArray  image,
std::vector< std::vector< double > > &  recognition_probabilities,
std::vector< int > &  oversegmentation 
)
virtual

The character classifier must return a (ranked list of) class(es) id('s)

Parameters
imageInput image CV_8UC1 or CV_8UC3 with a single letter.
recognition_probabilitiesFor each of the N characters found the classifier returns a list with class probabilities for each class.
oversegmentationThe classifier returns a list of N+1 character locations' x-coordinates, including 0 as start-sequence location.

§ getStepSize()

int cv::text::OCRBeamSearchDecoder::ClassifierCallback::getStepSize ( )
inline

§ getWindowSize()

int cv::text::OCRBeamSearchDecoder::ClassifierCallback::getWindowSize ( )
inline

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