Scene Text Recognition

Detailed Description

Classes
class	cv::text::BaseOCR
class	cv::text::OCRBeamSearchDecoder
	OCRBeamSearchDecoder class provides an interface for OCR using Beam Search algorithm. More...
class	cv::text::OCRHMMDecoder
	OCRHMMDecoder class provides an interface for OCR using Hidden Markov Models. More...
class	cv::text::OCRHolisticWordRecognizer
	OCRHolisticWordRecognizer class provides the functionallity of segmented wordspotting. Given a predefined vocabulary , a DictNet is employed to select the most probable word given an input image. More...
class	cv::text::OCRTesseract
	OCRTesseract class provides an interface with the tesseract-ocr API (v3.02.02) in C++. More...

Enumerations
enum	{   cv::text::OCR_LEVEL_WORD ,   cv::text::OCR_LEVEL_TEXTLINE }
enum	cv::text::classifier_type {   cv::text::OCR_KNN_CLASSIFIER = 0 ,   cv::text::OCR_CNN_CLASSIFIER = 1 }
enum	cv::text::decoder_mode { cv::text::OCR_DECODER_VITERBI = 0 }
enum	cv::text::ocr_engine_mode {   cv::text::OEM_TESSERACT_ONLY ,   cv::text::OEM_CUBE_ONLY ,   cv::text::OEM_TESSERACT_CUBE_COMBINED ,   cv::text::OEM_DEFAULT }
	Tesseract.OcrEngineMode Enumeration. More...
enum	cv::text::page_seg_mode {   cv::text::PSM_OSD_ONLY ,   cv::text::PSM_AUTO_OSD ,   cv::text::PSM_AUTO_ONLY ,   cv::text::PSM_AUTO ,   cv::text::PSM_SINGLE_COLUMN ,   cv::text::PSM_SINGLE_BLOCK_VERT_TEXT ,   cv::text::PSM_SINGLE_BLOCK ,   cv::text::PSM_SINGLE_LINE ,   cv::text::PSM_SINGLE_WORD ,   cv::text::PSM_CIRCLE_WORD ,   cv::text::PSM_SINGLE_CHAR }
	Tesseract.PageSegMode Enumeration. More...

Functions
Mat	cv::text::createOCRHMMTransitionsTable (const String &vocabulary, std::vector< cv::String > &lexicon)
void	cv::text::createOCRHMMTransitionsTable (std::string &vocabulary, std::vector< std::string > &lexicon, OutputArray transition_probabilities_table)
	Utility function to create a tailored language model transitions table from a given list of words (lexicon).
Ptr< OCRBeamSearchDecoder::ClassifierCallback >	cv::text::loadOCRBeamSearchClassifierCNN (const String &filename)
	Allow to implicitly load the default character classifier when creating an OCRBeamSearchDecoder object.
Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifier (const String &filename, int classifier)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.
Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifierCNN (const String &filename)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.
Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifierNM (const String &filename)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Enumeration Type Documentation

anonymous enum

anonymous enum

#include <opencv2/text/ocr.hpp>

Enumerator
OCR_LEVEL_WORD  Python: cv.text.OCR_LEVEL_WORD
OCR_LEVEL_TEXTLINE  Python: cv.text.OCR_LEVEL_TEXTLINE

classifier_type

enum cv::text::classifier_type

#include <opencv2/text/ocr.hpp>

Enumerator
OCR_KNN_CLASSIFIER  Python: cv.text.OCR_KNN_CLASSIFIER
OCR_CNN_CLASSIFIER  Python: cv.text.OCR_CNN_CLASSIFIER

decoder_mode

enum cv::text::decoder_mode

#include <opencv2/text/ocr.hpp>

Enumerator
OCR_DECODER_VITERBI  Python: cv.text.OCR_DECODER_VITERBI

ocr_engine_mode

enum cv::text::ocr_engine_mode

#include <opencv2/text/ocr.hpp>

Tesseract.OcrEngineMode Enumeration.

Enumerator
OEM_TESSERACT_ONLY  Python: cv.text.OEM_TESSERACT_ONLY
OEM_CUBE_ONLY  Python: cv.text.OEM_CUBE_ONLY
OEM_TESSERACT_CUBE_COMBINED  Python: cv.text.OEM_TESSERACT_CUBE_COMBINED
OEM_DEFAULT  Python: cv.text.OEM_DEFAULT

page_seg_mode

enum cv::text::page_seg_mode

#include <opencv2/text/ocr.hpp>

Tesseract.PageSegMode Enumeration.

Enumerator
PSM_OSD_ONLY  Python: cv.text.PSM_OSD_ONLY
PSM_AUTO_OSD  Python: cv.text.PSM_AUTO_OSD
PSM_AUTO_ONLY  Python: cv.text.PSM_AUTO_ONLY
PSM_AUTO  Python: cv.text.PSM_AUTO
PSM_SINGLE_COLUMN  Python: cv.text.PSM_SINGLE_COLUMN
PSM_SINGLE_BLOCK_VERT_TEXT  Python: cv.text.PSM_SINGLE_BLOCK_VERT_TEXT
PSM_SINGLE_BLOCK  Python: cv.text.PSM_SINGLE_BLOCK
PSM_SINGLE_LINE  Python: cv.text.PSM_SINGLE_LINE
PSM_SINGLE_WORD  Python: cv.text.PSM_SINGLE_WORD
PSM_CIRCLE_WORD  Python: cv.text.PSM_CIRCLE_WORD
PSM_SINGLE_CHAR  Python: cv.text.PSM_SINGLE_CHAR

Function Documentation

createOCRHMMTransitionsTable() [1/2]

Mat cv::text::createOCRHMMTransitionsTable	(	const String &	vocabulary,
		std::vector< cv::String > &	lexicon )

Python:
	cv.text.createOCRHMMTransitionsTable(	vocabulary, lexicon	) ->	retval

#include <opencv2/text/ocr.hpp>

createOCRHMMTransitionsTable() [2/2]

void cv::text::createOCRHMMTransitionsTable	(	std::string &	vocabulary,
		std::vector< std::string > &	lexicon,
		OutputArray	transition_probabilities_table )

Python:
	cv.text.createOCRHMMTransitionsTable(	vocabulary, lexicon	) ->	retval

#include <opencv2/text/ocr.hpp>

Utility function to create a tailored language model transitions table from a given list of words (lexicon).

Parameters

vocabulary	The language vocabulary (chars when ASCII English text).
lexicon	The list of words that are expected to be found in a particular image.
transition_probabilities_table	Output table with transition probabilities between character pairs. cols == rows == vocabulary.size().

The function calculate frequency statistics of character pairs from the given lexicon and fills the output transition_probabilities_table with them. The transition_probabilities_table can be used as input in the OCRHMMDecoder::create() and OCRBeamSearchDecoder::create() methods.

Note

• (C++) An alternative would be to load the default generic language transition table provided in the text module samples folder (created from ispell 42869 english words list) : https://github.com/opencv/opencv_contrib/blob/master/modules/text/samples/OCRHMM_transitions_table.xml

loadOCRBeamSearchClassifierCNN()

Ptr< OCRBeamSearchDecoder::ClassifierCallback > cv::text::loadOCRBeamSearchClassifierCNN

(

const String &

filename

)

Python:
	cv.text.loadOCRBeamSearchClassifierCNN(	filename	) ->	retval

#include <opencv2/text/ocr.hpp>

Allow to implicitly load the default character classifier when creating an OCRBeamSearchDecoder object.

Parameters

filename

The XML or YAML file with the classifier model (e.g. OCRBeamSearch_CNN_model_data.xml.gz)

The CNN default classifier is based in the scene text recognition method proposed by Adam Coates & Andrew NG in [Coates11a]. The character classifier consists in a Single Layer Convolutional Neural Network and a linear classifier. It is applied to the input image in a sliding window fashion, providing a set of recognitions at each window location.

loadOCRHMMClassifier()

Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifier	(	const String &	filename,
		int	classifier )

Python:
	cv.text.loadOCRHMMClassifier(	filename, classifier	) ->	retval

#include <opencv2/text/ocr.hpp>

Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Parameters

filename	The XML or YAML file with the classifier model (e.g. OCRBeamSearch_CNN_model_data.xml.gz)
classifier	Can be one of classifier_type enum values.

loadOCRHMMClassifierCNN()

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

(

const String &

filename

)

Python:
	cv.text.loadOCRHMMClassifierCNN(	filename	) ->	retval

#include <opencv2/text/ocr.hpp>

Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Parameters

filename

The XML or YAML file with the classifier model (e.g. OCRBeamSearch_CNN_model_data.xml.gz)

The CNN default classifier is based in the scene text recognition method proposed by Adam Coates & Andrew NG in [Coates11a]. The character classifier consists in a Single Layer Convolutional Neural Network and a linear classifier. It is applied to the input image in a sliding window fashion, providing a set of recognitions at each window location.

Deprecated

use loadOCRHMMClassifier instead

loadOCRHMMClassifierNM()

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

(

const String &

filename

)

Python:
	cv.text.loadOCRHMMClassifierNM(	filename	) ->	retval

#include <opencv2/text/ocr.hpp>

Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Parameters

filename

The XML or YAML file with the classifier model (e.g. OCRHMM_knn_model_data.xml)

The KNN default classifier is based in the scene text recognition method proposed by Lukás Neumann & Jiri Matas in [Neumann11b]. Basically, the region (contour) in the input image is normalized to a fixed size, while retaining the centroid and aspect ratio, in order to extract a feature vector based on gradient orientations along the chain-code of its perimeter. Then, the region is classified using a KNN model trained with synthetic data of rendered characters with different standard font types.

Deprecated

loadOCRHMMClassifier instead