OCRHMMDecoder class provides an interface for OCR using Hidden Markov Models. More...

#include <opencv2/text/ocr.hpp>

Inheritance diagram for cv::text::OCRHMMDecoder:

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

Public Member Functions
virtual void	run (Mat &image, std::string &output_text, std::vector< Rect > component_rects=NULL, std::vector< std::string > component_texts=NULL, std::vector< float > *component_confidences=NULL, int component_level=0) CV_OVERRIDE
	Recognize text using HMM. More...

virtual void	run (Mat &image, Mat &mask, std::string &output_text, std::vector< Rect > component_rects=NULL, std::vector< std::string > component_texts=NULL, std::vector< float > *component_confidences=NULL, int component_level=0) CV_OVERRIDE
	Recognize text using HMM. More...

String	run (InputArray image, int min_confidence, int component_level=0)

String	run (InputArray image, InputArray mask, int min_confidence, int component_level=0)

Public Member Functions inherited from cv::text::BaseOCR
virtual	~BaseOCR ()

Static Public Member Functions
static Ptr< OCRHMMDecoder >	create (const Ptr< OCRHMMDecoder::ClassifierCallback > classifier, const std::string &vocabulary, InputArray transition_probabilities_table, InputArray emission_probabilities_table, decoder_mode mode=OCR_DECODER_VITERBI)
	Creates an instance of the OCRHMMDecoder class. Initializes HMMDecoder. More...

static Ptr< OCRHMMDecoder >	create (const Ptr< OCRHMMDecoder::ClassifierCallback > classifier, const String &vocabulary, InputArray transition_probabilities_table, InputArray emission_probabilities_table, int mode=OCR_DECODER_VITERBI)

static Ptr< OCRHMMDecoder >	create (const String &filename, const String &vocabulary, InputArray transition_probabilities_table, InputArray emission_probabilities_table, int mode=OCR_DECODER_VITERBI, int classifier=OCR_KNN_CLASSIFIER)
	Creates an instance of the OCRHMMDecoder class. Loads and initializes HMMDecoder from the specified path. More...

Protected Attributes
Ptr< OCRHMMDecoder::ClassifierCallback >	classifier

Mat	emission_p

decoder_mode	mode

Mat	transition_p

std::string	vocabulary

Detailed Description

OCRHMMDecoder class provides an interface for OCR using Hidden Markov Models.

Note

(C++) An example on using OCRHMMDecoder recognition combined with scene text detection can be found at the webcam_demo sample: https://github.com/opencv/opencv_contrib/blob/master/modules/text/samples/webcam_demo.cpp

Member Function Documentation

◆ create() [1/3]

static Ptr<OCRHMMDecoder> cv::text::OCRHMMDecoder::create	(	const Ptr< OCRHMMDecoder::ClassifierCallback >	classifier,
		const std::string &	vocabulary,
		InputArray	transition_probabilities_table,
		InputArray	emission_probabilities_table,
		decoder_mode	mode = `OCR_DECODER_VITERBI`
	)

static

Python:
	retval	=	cv.text.OCRHMMDecoder_create(	classifier, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode]	)
	retval	=	cv.text.OCRHMMDecoder_create(	filename, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode[, classifier]]	)

Creates an instance of the OCRHMMDecoder class. Initializes HMMDecoder.

Parameters

classifier	The character classifier with built in feature extractor.
vocabulary	The language vocabulary (chars when ascii english text). vocabulary.size() must be equal to the number of classes of the classifier.
transition_probabilities_table	Table with transition probabilities between character pairs. cols == rows == vocabulary.size().
emission_probabilities_table	Table with observation emission probabilities. cols == rows == vocabulary.size().
mode	HMM Decoding algorithm. Only OCR_DECODER_VITERBI is available for the moment (http://en.wikipedia.org/wiki/Viterbi_algorithm).

◆ create() [2/3]

static Ptr<OCRHMMDecoder> cv::text::OCRHMMDecoder::create	(	const Ptr< OCRHMMDecoder::ClassifierCallback >	classifier,
		const String &	vocabulary,
		InputArray	transition_probabilities_table,
		InputArray	emission_probabilities_table,
		int	mode = `OCR_DECODER_VITERBI`
	)

static

Python:
	retval	=	cv.text.OCRHMMDecoder_create(	classifier, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode]	)
	retval	=	cv.text.OCRHMMDecoder_create(	filename, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode[, classifier]]	)

◆ create() [3/3]

static Ptr<OCRHMMDecoder> cv::text::OCRHMMDecoder::create	(	const String &	filename,
		const String &	vocabulary,
		InputArray	transition_probabilities_table,
		InputArray	emission_probabilities_table,
		int	mode = `OCR_DECODER_VITERBI`,
		int	classifier = `OCR_KNN_CLASSIFIER`
	)

static

Python:
	retval	=	cv.text.OCRHMMDecoder_create(	classifier, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode]	)
	retval	=	cv.text.OCRHMMDecoder_create(	filename, vocabulary, transition_probabilities_table, emission_probabilities_table[, mode[, classifier]]	)

Creates an instance of the OCRHMMDecoder class. Loads and initializes HMMDecoder from the specified path.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

◆ run() [1/4]

virtual void cv::text::OCRHMMDecoder::run	(	Mat &	image,
		std::string &	output_text,
		std::vector< Rect > *	component_rects = `NULL`,
		std::vector< std::string > *	component_texts = `NULL`,
		std::vector< float > *	component_confidences = `NULL`,
		int	component_level = `0`
	)

virtual

Python:
	retval	=	cv.text_OCRHMMDecoder.run(	image, min_confidence[, component_level]	)
	retval	=	cv.text_OCRHMMDecoder.run(	image, mask, min_confidence[, component_level]	)

Recognize text using HMM.

Takes binary image on input and returns recognized text in the output_text parameter. Optionally provides also the Rects for individual text elements found (e.g. words), and the list of those text elements with their confidence values.

Parameters

image	Input binary image CV_8UC1 with a single text line (or word).
output_text	Output text. Most likely character sequence found by the HMM decoder.
component_rects	If provided the method will output a list of Rects for the individual text elements found (e.g. words).
component_texts	If provided the method will output a list of text strings for the recognition of individual text elements found (e.g. words).
component_confidences	If provided the method will output a list of confidence values for the recognition of individual text elements found (e.g. words).
component_level	Only OCR_LEVEL_WORD is supported.

Implements cv::text::BaseOCR.

◆ run() [2/4]

virtual void cv::text::OCRHMMDecoder::run	(	Mat &	image,
		Mat &	mask,
		std::string &	output_text,
		std::vector< Rect > *	component_rects = `NULL`,
		std::vector< std::string > *	component_texts = `NULL`,
		std::vector< float > *	component_confidences = `NULL`,
		int	component_level = `0`
	)

virtual

Python:
	retval	=	cv.text_OCRHMMDecoder.run(	image, min_confidence[, component_level]	)
	retval	=	cv.text_OCRHMMDecoder.run(	image, mask, min_confidence[, component_level]	)

Recognize text using HMM.

Takes an image and a mask (where each connected component corresponds to a segmented character) on input and returns recognized text in the output_text parameter. Optionally provides also the Rects for individual text elements found (e.g. words), and the list of those text elements with their confidence values.

Parameters

image	Input image CV_8UC1 or CV_8UC3 with a single text line (or word).
mask	Input binary image CV_8UC1 same size as input image. Each connected component in mask corresponds to a segmented character in the input image.
output_text	Output text. Most likely character sequence found by the HMM decoder.
component_rects	If provided the method will output a list of Rects for the individual text elements found (e.g. words).
component_texts	If provided the method will output a list of text strings for the recognition of individual text elements found (e.g. words).
component_confidences	If provided the method will output a list of confidence values for the recognition of individual text elements found (e.g. words).
component_level	Only OCR_LEVEL_WORD is supported.

Implements cv::text::BaseOCR.

◆ run() [3/4]

String cv::text::OCRHMMDecoder::run	(	InputArray	image,
		int	min_confidence,
		int	component_level = `0`
	)

Python:
	retval	=	cv.text_OCRHMMDecoder.run(	image, min_confidence[, component_level]	)
	retval	=	cv.text_OCRHMMDecoder.run(	image, mask, min_confidence[, component_level]	)

◆ run() [4/4]

String cv::text::OCRHMMDecoder::run	(	InputArray	image,
		InputArray	mask,
		int	min_confidence,
		int	component_level = `0`
	)

Python:
	retval	=	cv.text_OCRHMMDecoder.run(	image, min_confidence[, component_level]	)
	retval	=	cv.text_OCRHMMDecoder.run(	image, mask, min_confidence[, component_level]	)

Member Data Documentation

◆ classifier

Ptr<OCRHMMDecoder::ClassifierCallback> cv::text::OCRHMMDecoder::classifier

protected

◆ emission_p

Mat cv::text::OCRHMMDecoder::emission_p

protected

◆ mode

decoder_mode cv::text::OCRHMMDecoder::mode

protected

◆ transition_p

Mat cv::text::OCRHMMDecoder::transition_p

protected

◆ vocabulary

std::string cv::text::OCRHMMDecoder::vocabulary

protected

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

opencv2/text/ocr.hpp

Classes

Public Member Functions

Static Public Member Functions

Protected Attributes

Detailed Description

Member Function Documentation

◆ create() [1/3]

◆ create() [2/3]

◆ create() [3/3]

◆ run() [1/4]

◆ run() [2/4]

◆ run() [3/4]

◆ run() [4/4]

Member Data Documentation

◆ classifier

◆ emission_p

◆ mode

◆ transition_p

◆ vocabulary