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...

#include <opencv2/text/ocr.hpp>

Collaboration diagram for cv::text::OCRHolisticWordRecognizer:

Public Member Functions
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=OCR_LEVEL_WORD) CV_OVERRIDE=0
	Recognize text using a segmentation based word-spotting/classifier cnn.

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=OCR_LEVEL_WORD) CV_OVERRIDE=0

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

Static Public Member Functions
static Ptr< OCRHolisticWordRecognizer >	create (const std::string &archFilename, const std::string &weightsFilename, const std::string &wordsFilename)
	Creates an instance of the OCRHolisticWordRecognizer class.

Detailed Description

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.

DictNet is described in detail in: Max Jaderberg et al.: Reading Text in the Wild with Convolutional Neural Networks, IJCV 2015 http://arxiv.org/abs/1412.1842

Member Function Documentation

◆ create()

static Ptr< OCRHolisticWordRecognizer > cv::text::OCRHolisticWordRecognizer::create	(	const std::string &	archFilename,
		const std::string &	weightsFilename,
		const std::string &	wordsFilename )

static

Creates an instance of the OCRHolisticWordRecognizer class.

◆ run() [1/2]

virtual void cv::text::OCRHolisticWordRecognizer::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 = OCR_LEVEL_WORD )

pure virtual

Recognize text using a segmentation based word-spotting/classifier cnn.

Takes 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 image CV_8UC1 or CV_8UC3
mask	is totally ignored and is only available for compatibillity reasons
output_text	Output text of the the word spoting, always one that exists in the dictionary.
component_rects	Not applicable for word spotting can be be NULL if not, a single elemnt will be put in the vector.
component_texts	Not applicable for word spotting can be be NULL if not, a single elemnt will be put in the vector.
component_confidences	Not applicable for word spotting can be be NULL if not, a single elemnt will be put in the vector.
component_level	must be OCR_LEVEL_WORD.

Implements cv::text::BaseOCR.

◆ run() [2/2]

virtual void cv::text::OCRHolisticWordRecognizer::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 = OCR_LEVEL_WORD )